Daily Papers

Laughing, sighing, stuttering, and other forms of paralanguage do not contribute any direct lexical meaning to speech, but they provide crucial propositional context that aids semantic and pragmatic processes such as irony. It is thus important for artificial social agents to both understand and be able to generate speech with semantically-important paralanguage. Most speech datasets do not include transcribed non-lexical speech sounds and disfluencies, while those that do are typically multi-speaker datasets where each speaker provides relatively little audio. This makes it challenging to train conversational Text-to-Speech (TTS) synthesis models that include such paralinguistic components. We thus present DisfluencySpeech, a studio-quality labeled English speech dataset with paralanguage. A single speaker recreates nearly 10 hours of expressive utterances from the Switchboard-1 Telephone Speech Corpus (Switchboard), simulating realistic informal conversations. To aid the development of a TTS model that is able to predictively synthesise paralanguage from text without such components, we provide three different transcripts at different levels of information removal (removal of non-speech events, removal of non-sentence elements, and removal of false starts), as well as benchmark TTS models trained on each of these levels.

Human spoken communication involves not only lexical content but also non-verbal vocalizations (NVs) such as laughter, sighs, and coughs, which convey emotions, intentions, and social signals. However, most existing speech systems focus solely on verbal content and lack the ability to understand and generate such non-verbal cues, reducing the emotional intelligence and communicative richness of spoken interfaces. In this work, we introduce NonVerbalSpeech-38K, a large and diverse dataset for non-verbal speech generation and understanding, collected from real-world media and annotated using an automatic pipeline. The dataset contains 38,718 samples (about 131 hours) with 10 categories of non-verbal cues, such as laughter, sniff, and throat clearing. We further validate the dataset by fine-tuning state-of-the-art models, including F5-TTS and Qwen2-Audio, demonstrating its effectiveness in non-verbal speech generation and understanding tasks. Our contributions are threefold: (1) We propose a practical pipeline for building natural and diverse non-verbal speech datasets; (2) We release a large-scale dataset to advance research on non-verbal speech generation and understanding; (3) We validate the dataset's effectiveness by demonstrating improvements in both non-verbal speech synthesis and captioning, thereby facilitating richer human-computer interaction.

Speech conveys not only linguistic information but also rich non-verbal vocal events such as laughing and crying. While semantic transcription is well-studied, the precise localization of non-verbal events remains a critical yet under-explored challenge. Current methods suffer from insufficient task definitions with limited category coverage and ambiguous temporal granularity. They also lack standardized evaluation frameworks, hindering the development of downstream applications. To bridge this gap, we first develop a refined taxonomy of 21 vocal events, with a new categorization into discrete (standalone) versus continuous (mixed with speech) types. Based on the refined taxonomy, we introduce WESR-Bench, an expert-annotated evaluation set (900+ utterances) with a novel position-aware protocol that disentangles ASR errors from event detection, enabling precise localization measurement for both discrete and continuous events. We also build a strong baseline by constructing a 1,700+ hour corpus, and train specialized models, surpassing both open-source audio-language models and commercial APIs while preserving ASR quality. We anticipate that WESR will serve as a foundational resource for future research in modeling rich, real-world auditory scenes.

We present SoundStorm, a model for efficient, non-autoregressive audio generation. SoundStorm receives as input the semantic tokens of AudioLM, and relies on bidirectional attention and confidence-based parallel decoding to generate the tokens of a neural audio codec. Compared to the autoregressive generation approach of AudioLM, our model produces audio of the same quality and with higher consistency in voice and acoustic conditions, while being two orders of magnitude faster. SoundStorm generates 30 seconds of audio in 0.5 seconds on a TPU-v4. We demonstrate the ability of our model to scale audio generation to longer sequences by synthesizing high-quality, natural dialogue segments, given a transcript annotated with speaker turns and a short prompt with the speakers' voices.

Paralinguistic vocalizations-including non-verbal sounds like laughter and breathing, as well as lexicalized interjections such as "uhm" and "oh"-are integral to natural spoken communication. Despite their importance in conveying affect, intent, and interactional cues, such cues remain largely overlooked in conventional automatic speech recognition (ASR) and text-to-speech (TTS) systems. We present NVSpeech, an integrated and scalable pipeline that bridges the recognition and synthesis of paralinguistic vocalizations, encompassing dataset construction, ASR modeling, and controllable TTS. (1) We introduce a manually annotated dataset of 48,430 human-spoken utterances with 18 word-level paralinguistic categories. (2) We develop the paralinguistic-aware ASR model, which treats paralinguistic cues as inline decodable tokens (e.g., "You're so funny [Laughter]"), enabling joint lexical and non-verbal transcription. This model is then used to automatically annotate a large corpus, the first large-scale Chinese dataset of 174,179 utterances (573 hours) with word-level alignment and paralingustic cues. (3) We finetune zero-shot TTS models on both human- and auto-labeled data to enable explicit control over paralinguistic vocalizations, allowing context-aware insertion at arbitrary token positions for human-like speech synthesis. By unifying the recognition and generation of paralinguistic vocalizations, NVSpeech offers the first open, large-scale, word-level annotated pipeline for expressive speech modeling in Mandarin, integrating recognition and synthesis in a scalable and controllable manner. Dataset and audio demos are available at https://nvspeech170k.github.io/.

Speech sounds convey a great deal of information about the scenes, resulting in a variety of effects ranging from reverberation to additional ambient sounds. In this paper, we manipulate input speech to sound as though it was recorded within a different scene, given an audio-visual conditional example recorded from that scene. Our model learns through self-supervision, taking advantage of the fact that natural video contains recurring sound events and textures. We extract an audio clip from a video and apply speech enhancement. We then train a latent diffusion model to recover the original speech, using another audio-visual clip taken from elsewhere in the video as a conditional hint. Through this process, the model learns to transfer the conditional example's sound properties to the input speech. We show that our model can be successfully trained using unlabeled, in-the-wild videos, and that an additional visual signal can improve its sound prediction abilities. Please see our project webpage for video results: https://tinglok.netlify.app/files/avsoundscape/

Traditionally, bioacoustics has relied on spectrograms and continuous, per-frame audio representations for the analysis of animal sounds, also serving as input to machine learning models. Meanwhile, the International Phonetic Alphabet (IPA) system has provided an interpretable, language-independent method for transcribing human speech sounds. In this paper, we introduce ISPA (Inter-Species Phonetic Alphabet), a precise, concise, and interpretable system designed for transcribing animal sounds into text. We compare acoustics-based and feature-based methods for transcribing and classifying animal sounds, demonstrating their comparable performance with baseline methods utilizing continuous, dense audio representations. By representing animal sounds with text, we effectively treat them as a "foreign language," and we show that established human language ML paradigms and models, such as language models, can be successfully applied to improve performance.

Non-verbal signals in speech are encoded by prosody and carry information that ranges from conversation action to attitude and emotion. Despite its importance, the principles that govern prosodic structure are not yet adequately understood. This paper offers an analytical schema and a technological proof-of-concept for the categorization of prosodic signals and their association with meaning. The schema interprets surface-representations of multi-layered prosodic events. As a first step towards implementation, we present a classification process that disentangles prosodic phenomena of three orders. It relies on fine-tuning a pre-trained speech recognition model, enabling the simultaneous multi-class/multi-label detection. It generalizes over a large variety of spontaneous data, performing on a par with, or superior to, human annotation. In addition to a standardized formalization of prosody, disentangling prosodic patterns can direct a theory of communication and speech organization. A welcome by-product is an interpretation of prosody that will enhance speech- and language-related technologies.

Historically, most speech models in machine-learning have used the mel-spectrogram as a speech representation. Recently, discrete audio tokens produced by neural audio codecs have become a popular alternate speech representation for speech synthesis tasks such as text-to-speech (TTS). However, the data distribution produced by such codecs is too complex for some TTS models to predict, hence requiring large autoregressive models to get reasonable quality. Typical audio codecs compress and reconstruct the time-domain audio signal. We propose a spectral codec which compresses the mel-spectrogram and reconstructs the time-domain audio signal. A study of objective audio quality metrics suggests that our spectral codec has comparable perceptual quality to equivalent audio codecs. Furthermore, non-autoregressive TTS models trained with the proposed spectral codec generate audio with significantly higher quality than when trained with mel-spectrograms or audio codecs.

Generative models have shown remarkable performance in speech enhancement (SE), achieving superior perceptual quality over traditional discriminative approaches. However, existing generative SE approaches often overlook the risk of hallucination under severe noise, leading to incorrect spoken content or inconsistent speaker characteristics, which we term linguistic and acoustic hallucinations, respectively. We argue that linguistic hallucination stems from models' failure to constrain valid phonological structures and it is a more fundamental challenge. While language models (LMs) are well-suited for capturing the underlying speech structure through modeling the distribution of discrete tokens, existing approaches are limited in learning from noise-corrupted representations, which can lead to contaminated priors and hallucinations. To overcome these limitations, we propose the Phonologically Anchored Speech Enhancer (PASE), a generative SE framework that leverages the robust phonological prior embedded in the pre-trained WavLM model to mitigate hallucinations. First, we adapt WavLM into a denoising expert via representation distillation to clean its final-layer features. Guided by the model's intrinsic phonological prior, this process enables robust denoising while minimizing linguistic hallucinations. To further reduce acoustic hallucinations, we train the vocoder with a dual-stream representation: the high-level phonetic representation provides clean linguistic content, while a low-level acoustic representation retains speaker identity and prosody. Experimental results demonstrate that PASE not only surpasses state-of-the-art discriminative models in perceptual quality, but also significantly outperforms prior generative models with substantially lower linguistic and acoustic hallucinations.

Mainstream Automatic Speech Recognition (ASR) systems excel at transcribing lexical content, but largely fail to recognize nonverbal vocalizations (NVs) embedded in speech, such as sighs, laughs, and coughs. This capability is important for a comprehensive understanding of human communication, as NVs convey crucial emotional and intentional cues. Progress in NV-aware ASR has been hindered by the lack of high-quality, well-annotated datasets. To address this gap, we introduce MNV-17, a 7.55-hour performative Mandarin speech dataset. Unlike most existing corpora that rely on model-based detection, MNV-17's performative nature ensures high-fidelity, clearly articulated NV instances. To the best of our knowledge, MNV-17 provides the most extensive set of nonverbal vocalization categories, comprising 17 distinct and well-balanced classes of common NVs. We benchmarked MNV-17 on four mainstream ASR architectures, evaluating their joint performance on semantic transcription and NV classification. The dataset and the pretrained model checkpoints will be made publicly available to facilitate future research in expressive ASR.

Humans are surrounded by audio signals that include both speech and non-speech sounds. The recognition and understanding of speech and non-speech audio events, along with a profound comprehension of the relationship between them, constitute fundamental cognitive capabilities. For the first time, we build a machine learning model, called LTU-AS, that has a conceptually similar universal audio perception and advanced reasoning ability. Specifically, by integrating Whisper as a perception module and LLaMA as a reasoning module, LTU-AS can simultaneously recognize and jointly understand spoken text, speech paralinguistics, and non-speech audio events - almost everything perceivable from audio signals.

Paralinguistic sounds, like laughter and sighs, are crucial for synthesizing more realistic and engaging speech. However, existing methods typically depend on proprietary datasets, while publicly available resources often suffer from incomplete speech, inaccurate or missing timestamps, and limited real-world relevance. To address these problems, we propose an automated framework for generating large-scale paralinguistic data and apply it to construct the SynParaSpeech dataset. The dataset comprises 6 paralinguistic categories with 118.75 hours of data and precise timestamps, all derived from natural conversational speech. Our contributions lie in introducing the first automated method for constructing large-scale paralinguistic datasets and releasing the SynParaSpeech corpus, which advances speech generation through more natural paralinguistic synthesis and enhances speech understanding by improving paralinguistic event detection. The dataset and audio samples are available at https://github.com/ShawnPi233/SynParaSpeech.

We propose TalkNet, a non-autoregressive convolutional neural model for speech synthesis with explicit pitch and duration prediction. The model consists of three feed-forward convolutional networks. The first network predicts grapheme durations. An input text is expanded by repeating each symbol according to the predicted duration. The second network predicts pitch value for every mel frame. The third network generates a mel-spectrogram from the expanded text conditioned on predicted pitch. All networks are based on 1D depth-wise separable convolutional architecture. The explicit duration prediction eliminates word skipping and repeating. The quality of the generated speech nearly matches the best auto-regressive models - TalkNet trained on the LJSpeech dataset got MOS 4.08. The model has only 13.2M parameters, almost 2x less than the present state-of-the-art text-to-speech models. The non-autoregressive architecture allows for fast training and inference. The small model size and fast inference make the TalkNet an attractive candidate for embedded speech synthesis.

Interpretability research has shown that self-supervised Spoken Language Models (SLMs) encode a wide variety of features in human speech from the acoustic, phonetic, phonological, syntactic and semantic levels, to speaker characteristics. The bulk of prior research on representations of phonology has focused on segmental features such as phonemes; the encoding of suprasegmental phonology (such as tone and stress patterns) in SLMs is not yet well understood. Tone is a suprasegmental feature that is present in more than half of the world's languages. This paper aims to analyze the tone encoding capabilities of SLMs, using Mandarin and Vietnamese as case studies. We show that SLMs encode lexical tone to a significant degree even when they are trained on data from non-tonal languages. We further find that SLMs behave similarly to native and non-native human participants in tone and consonant perception studies, but they do not follow the same developmental trajectory.

Representing wild sounds as images is an important but challenging task due to the lack of paired datasets between sound and images and the significant differences in the characteristics of these two modalities. Previous studies have focused on generating images from sound in limited categories or music. In this paper, we propose a novel approach to generate images from in-the-wild sounds. First, we convert sound into text using audio captioning. Second, we propose audio attention and sentence attention to represent the rich characteristics of sound and visualize the sound. Lastly, we propose a direct sound optimization with CLIPscore and AudioCLIP and generate images with a diffusion-based model. In experiments, it shows that our model is able to generate high quality images from wild sounds and outperforms baselines in both quantitative and qualitative evaluations on wild audio datasets.

With read-aloud speech synthesis achieving high naturalness scores, there is a growing research interest in synthesising spontaneous speech. However, human spontaneous face-to-face conversation has both spoken and non-verbal aspects (here, co-speech gestures). Only recently has research begun to explore the benefits of jointly synthesising these two modalities in a single system. The previous state of the art used non-probabilistic methods, which fail to capture the variability of human speech and motion, and risk producing oversmoothing artefacts and sub-optimal synthesis quality. We present the first diffusion-based probabilistic model, called Diff-TTSG, that jointly learns to synthesise speech and gestures together. Our method can be trained on small datasets from scratch. Furthermore, we describe a set of careful uni- and multi-modal subjective tests for evaluating integrated speech and gesture synthesis systems, and use them to validate our proposed approach. Please see https://shivammehta25.github.io/Diff-TTSG/ for video examples, data, and code.

Speech foundation models have demonstrated exceptional capabilities in speech-related tasks. Nevertheless, these models often struggle with non-verbal audio data, such as vocalizations, baby crying, etc., which are critical for various real-world applications. Audio foundation models well handle non-speech data but also fail to capture the nuanced features of non-verbal human sounds. In this work, we aim to overcome the above shortcoming and propose a novel foundation model, termed voc2vec, specifically designed for non-verbal human data leveraging exclusively open-source non-verbal audio datasets. We employ a collection of 10 datasets covering around 125 hours of non-verbal audio. Experimental results prove that voc2vec is effective in non-verbal vocalization classification, and it outperforms conventional speech and audio foundation models. Moreover, voc2vec consistently outperforms strong baselines, namely OpenSmile and emotion2vec, on six different benchmark datasets. To the best of the authors' knowledge, voc2vec is the first universal representation model for vocalization tasks.

We examine the text-free speech representations of raw audio obtained from a self-supervised learning (SSL) model by analyzing the synthesized speech using the SSL representations instead of conventional text representations. Since raw audio does not have paired speech representations as transcribed texts do, obtaining speech representations from unpaired speech is crucial for augmenting available datasets for speech synthesis. Specifically, the proposed speech synthesis is conducted using discrete symbol representations from the SSL model in comparison with text representations, and analytical examinations of the synthesized speech have been carried out. The results empirically show that using text representations is advantageous for preserving semantic information, while using discrete symbol representations is superior for preserving acoustic content, including prosodic and intonational information.

Hallucinations of deep neural models are amongst key challenges in automatic speech recognition (ASR). In this paper, we investigate hallucinations of the Whisper ASR model induced by non-speech audio segments present during inference. By inducting hallucinations with various types of sounds, we show that there exists a set of hallucinations that appear frequently. We then study hallucinations caused by the augmentation of speech with such sounds. Finally, we describe the creation of a bag of hallucinations (BoH) that allows to remove the effect of hallucinations through the post-processing of text transcriptions. The results of our experiments show that such post-processing is capable of reducing word error rate (WER) and acts as a good safeguard against problematic hallucinations.

Non-linguistic filler words, such as "uh" or "um", are prevalent in spontaneous speech and serve as indicators for expressing hesitation or uncertainty. Previous works for detecting certain non-linguistic filler words are highly dependent on transcriptions from a well-established commercial automatic speech recognition (ASR) system. However, certain ASR systems are not universally accessible from many aspects, e.g., budget, target languages, and computational power. In this work, we investigate filler word detection system that does not depend on ASR systems. We show that, by using the structured state space sequence model (S4) and neural semi-Markov conditional random fields (semi-CRFs), we achieve an absolute F1 improvement of 6.4% (segment level) and 3.1% (event level) on the PodcastFillers dataset. We also conduct a qualitative analysis on the detected results to analyze the limitations of our proposed system.

In this study, we propose a simple and efficient Non-Autoregressive (NAR) text-to-speech (TTS) system based on diffusion, named SimpleSpeech. Its simpleness shows in three aspects: (1) It can be trained on the speech-only dataset, without any alignment information; (2) It directly takes plain text as input and generates speech through an NAR way; (3) It tries to model speech in a finite and compact latent space, which alleviates the modeling difficulty of diffusion. More specifically, we propose a novel speech codec model (SQ-Codec) with scalar quantization, SQ-Codec effectively maps the complex speech signal into a finite and compact latent space, named scalar latent space. Benefits from SQ-Codec, we apply a novel transformer diffusion model in the scalar latent space of SQ-Codec. We train SimpleSpeech on 4k hours of a speech-only dataset, it shows natural prosody and voice cloning ability. Compared with previous large-scale TTS models, it presents significant speech quality and generation speed improvement. Demos are released.

Hallucinations are a type of output error produced by deep neural networks. While this has been studied in natural language processing, they have not been researched previously in automatic speech recognition. Here, we define hallucinations in ASR as transcriptions generated by a model that are semantically unrelated to the source utterance, yet still fluent and coherent. The similarity of hallucinations to probable natural language outputs of the model creates a danger of deception and impacts the credibility of the system. We show that commonly used metrics, such as word error rates, cannot differentiate between hallucinatory and non-hallucinatory models. To address this, we propose a perturbation-based method for assessing the susceptibility of an automatic speech recognition (ASR) model to hallucination at test time, which does not require access to the training dataset. We demonstrate that this method helps to distinguish between hallucinatory and non-hallucinatory models that have similar baseline word error rates. We further explore the relationship between the types of ASR errors and the types of dataset noise to determine what types of noise are most likely to create hallucinatory outputs. We devise a framework for identifying hallucinations by analysing their semantic connection with the ground truth and their fluency. Finally, we discover how to induce hallucinations with a random noise injection to the utterance.

This paper introduces Embarrassingly Easy Text-to-Speech (E2 TTS), a fully non-autoregressive zero-shot text-to-speech system that offers human-level naturalness and state-of-the-art speaker similarity and intelligibility. In the E2 TTS framework, the text input is converted into a character sequence with filler tokens. The flow-matching-based mel spectrogram generator is then trained based on the audio infilling task. Unlike many previous works, it does not require additional components (e.g., duration model, grapheme-to-phoneme) or complex techniques (e.g., monotonic alignment search). Despite its simplicity, E2 TTS achieves state-of-the-art zero-shot TTS capabilities that are comparable to or surpass previous works, including Voicebox and NaturalSpeech 3. The simplicity of E2 TTS also allows for flexibility in the input representation. We propose several variants of E2 TTS to improve usability during inference. See https://aka.ms/e2tts/ for demo samples.

Self-supervised speech representations have been shown to be effective in a variety of speech applications. However, existing representation learning methods generally rely on the autoregressive model and/or observed global dependencies while generating the representation. In this work, we propose Non-Autoregressive Predictive Coding (NPC), a self-supervised method, to learn a speech representation in a non-autoregressive manner by relying only on local dependencies of speech. NPC has a conceptually simple objective and can be implemented easily with the introduced Masked Convolution Blocks. NPC offers a significant speedup for inference since it is parallelizable in time and has a fixed inference time for each time step regardless of the input sequence length. We discuss and verify the effectiveness of NPC by theoretically and empirically comparing it with other methods. We show that the NPC representation is comparable to other methods in speech experiments on phonetic and speaker classification while being more efficient.

Spectrograms are 2D representations of sound that look very different from the images found in our visual world. And natural images, when played as spectrograms, make unnatural sounds. In this paper, we show that it is possible to synthesize spectrograms that simultaneously look like natural images and sound like natural audio. We call these spectrograms images that sound. Our approach is simple and zero-shot, and it leverages pre-trained text-to-image and text-to-spectrogram diffusion models that operate in a shared latent space. During the reverse process, we denoise noisy latents with both the audio and image diffusion models in parallel, resulting in a sample that is likely under both models. Through quantitative evaluations and perceptual studies, we find that our method successfully generates spectrograms that align with a desired audio prompt while also taking the visual appearance of a desired image prompt. Please see our project page for video results: https://ificl.github.io/images-that-sound/

This paper introduces FT Speech, a new speech corpus created from the recorded meetings of the Danish Parliament, otherwise known as the Folketing (FT). The corpus contains over 1,800 hours of transcribed speech by a total of 434 speakers. It is significantly larger in duration, vocabulary, and amount of spontaneous speech than the existing public speech corpora for Danish, which are largely limited to read-aloud and dictation data. We outline design considerations, including the preprocessing methods and the alignment procedure. To evaluate the quality of the corpus, we train automatic speech recognition systems on the new resource and compare them to the systems trained on the Danish part of Sprakbanken, the largest public ASR corpus for Danish to date. Our baseline results show that we achieve a 14.01 WER on the new corpus. A combination of FT Speech with in-domain language data provides comparable results to models trained specifically on Sprakbanken, showing that FT Speech transfers well to this data set. Interestingly, our results demonstrate that the opposite is not the case. This shows that FT Speech provides a valuable resource for promoting research on Danish ASR with more spontaneous speech.

Recognizing human non-speech vocalizations is an important task and has broad applications such as automatic sound transcription and health condition monitoring. However, existing datasets have a relatively small number of vocal sound samples or noisy labels. As a consequence, state-of-the-art audio event classification models may not perform well in detecting human vocal sounds. To support research on building robust and accurate vocal sound recognition, we have created a VocalSound dataset consisting of over 21,000 crowdsourced recordings of laughter, sighs, coughs, throat clearing, sneezes, and sniffs from 3,365 unique subjects. Experiments show that the vocal sound recognition performance of a model can be significantly improved by 41.9% by adding VocalSound dataset to an existing dataset as training material. In addition, different from previous datasets, the VocalSound dataset contains meta information such as speaker age, gender, native language, country, and health condition.

What do deep neural speech models know about phonology? Existing work has examined the encoding of individual linguistic units such as phonemes in these models. Here we investigate interactions between units. Inspired by classic experiments on human speech perception, we study how Wav2Vec2 resolves phonotactic constraints. We synthesize sounds on an acoustic continuum between /l/ and /r/ and embed them in controlled contexts where only /l/, only /r/, or neither occur in English. Like humans, Wav2Vec2 models show a bias towards the phonotactically admissable category in processing such ambiguous sounds. Using simple measures to analyze model internals on the level of individual stimuli, we find that this bias emerges in early layers of the model's Transformer module. This effect is amplified by ASR finetuning but also present in fully self-supervised models. Our approach demonstrates how controlled stimulus designs can help localize specific linguistic knowledge in neural speech models.

We propose a novel text-to-speech (TTS) framework centered around a neural transducer. Our approach divides the whole TTS pipeline into semantic-level sequence-to-sequence (seq2seq) modeling and fine-grained acoustic modeling stages, utilizing discrete semantic tokens obtained from wav2vec2.0 embeddings. For a robust and efficient alignment modeling, we employ a neural transducer named token transducer for the semantic token prediction, benefiting from its hard monotonic alignment constraints. Subsequently, a non-autoregressive (NAR) speech generator efficiently synthesizes waveforms from these semantic tokens. Additionally, a reference speech controls temporal dynamics and acoustic conditions at each stage. This decoupled framework reduces the training complexity of TTS while allowing each stage to focus on semantic and acoustic modeling. Our experimental results on zero-shot adaptive TTS demonstrate that our model surpasses the baseline in terms of speech quality and speaker similarity, both objectively and subjectively. We also delve into the inference speed and prosody control capabilities of our approach, highlighting the potential of neural transducers in TTS frameworks.

This work aims to advance sound event detection (SED) research by presenting a new large language model (LLM)-powered dataset namely wild domestic environment sound event detection (WildDESED). It is crafted as an extension to the original DESED dataset to reflect diverse acoustic variability and complex noises in home settings. We leveraged LLMs to generate eight different domestic scenarios based on target sound categories of the DESED dataset. Then we enriched the scenarios with a carefully tailored mixture of noises selected from AudioSet and ensured no overlap with target sound. We consider widely popular convolutional neural recurrent network to study WildDESED dataset, which depicts its challenging nature. We then apply curriculum learning by gradually increasing noise complexity to enhance the model's generalization capabilities across various noise levels. Our results with this approach show improvements within the noisy environment, validating the effectiveness on the WildDESED dataset promoting noise-robust SED advancements.

In recent years, there has been growing interest in representing speech with discrete tokens, which serve as pseudo-text for speech language models (speechLMs) and as efficient intermediate representations for downstream tasks. These tokens are typically categorized as acoustic and phonetic tokens: the former holds detailed acoustic information for reconstruction while the latter mainly captures linguistic content. In human speech communication, however, unnecessary acoustic details such as speaker information are abstracted, while both linguistic and prosodic information are utilized for speech comprehension and production. Given this, neither type of token seems an ideal representation for tasks sensitive to prosody, such as speechLMs. In this study, we propose the Phonological Tokenizer, a method that fine-tunes phonetic tokens via differentiable k-means with a multi-task objective of ASR and speech resynthesis. Experimental validation on diverse tasks confirms that our tokens retain phonological (both linguistic and prosodic) information while appropriately discarding speaker identity.

Large audio-language models (LALMs) unify speech and text processing, but their robustness in noisy real-world settings remains underexplored. We investigate how irrelevant audio, such as silence, synthetic noise, and environmental sounds, affects text reasoning tasks where audio is unnecessary. Across three text-based benchmarks, we find that even non-informative audio reduces accuracy and increases prediction volatility; the severity of interference scales with longer durations, higher amplitudes, and elevated decoding temperatures. Silence, often assumed neutral, destabilizes outputs as strongly as synthetic noise. While larger models show greater resilience, vulnerabilities persist across all evaluated systems. We further test mitigation strategies and find that prompting shows limited effectiveness, whereas self-consistency improves stability at the cost of increased computation. Our results reveal cross-modal interference as a key robustness challenge and highlight the need for efficient fusion strategies that preserve reasoning performance in the presence of irrelevant inputs.

Research on pronunciation assessment systems focuses on utilizing phonetic and phonological aspects of non-native (L2) speech, often neglecting the rich layer of information hidden within the non-verbal cues. In this study, we proposed a novel pronunciation assessment framework, IntraVerbalPA. % The framework innovatively incorporates both fine-grained frame- and abstract utterance-level non-verbal cues, alongside the conventional speech and phoneme representations. Additionally, we introduce ''Goodness of phonemic-duration'' metric to effectively model duration distribution within the framework. Our results validate the effectiveness of the proposed IntraVerbalPA framework and its individual components, yielding performance that either matches or outperforms existing research works.

Open-vocabulary audio-language models, like CLAP, offer a promising approach for zero-shot audio classification (ZSAC) by enabling classification with any arbitrary set of categories specified with natural language prompts. In this paper, we propose a simple but effective method to improve ZSAC with CLAP. Specifically, we shift from the conventional method of using prompts with abstract category labels (e.g., Sound of an organ) to prompts that describe sounds using their inherent descriptive features in a diverse context (e.g.,The organ's deep and resonant tones filled the cathedral.). To achieve this, we first propose ReCLAP, a CLAP model trained with rewritten audio captions for improved understanding of sounds in the wild. These rewritten captions describe each sound event in the original caption using their unique discriminative characteristics. ReCLAP outperforms all baselines on both multi-modal audio-text retrieval and ZSAC. Next, to improve zero-shot audio classification with ReCLAP, we propose prompt augmentation. In contrast to the traditional method of employing hand-written template prompts, we generate custom prompts for each unique label in the dataset. These custom prompts first describe the sound event in the label and then employ them in diverse scenes. Our proposed method improves ReCLAP's performance on ZSAC by 1%-18% and outperforms all baselines by 1% - 55%.

Even without directly hearing sounds, humans can effortlessly reason about auditory properties, such as pitch, loudness, or sound-source associations, drawing on auditory commonsense. In contrast, language models often lack this capability, limiting their effectiveness in multimodal interactions. As an initial step to address this gap, we present AuditoryBench++, a comprehensive benchmark for evaluating auditory knowledge and reasoning in text-only settings. The benchmark encompasses tasks that range from basic auditory comparisons to contextually grounded reasoning, enabling fine-grained analysis of how models process and integrate auditory concepts. In addition, we introduce AIR-CoT, a novel auditory imagination reasoning method that generates and integrates auditory information during inference through span detection with special tokens and knowledge injection. Extensive experiments with recent LLMs and Multimodal LLMs demonstrate that AIR-CoT generally outperforms both the off-the-shelf models and those augmented with auditory knowledge. The project page is available at https://auditorybenchpp.github.io.

This paper introduces Easy One-Step Text-to-Speech (E1 TTS), an efficient non-autoregressive zero-shot text-to-speech system based on denoising diffusion pretraining and distribution matching distillation. The training of E1 TTS is straightforward; it does not require explicit monotonic alignment between the text and audio pairs. The inference of E1 TTS is efficient, requiring only one neural network evaluation for each utterance. Despite its sampling efficiency, E1 TTS achieves naturalness and speaker similarity comparable to various strong baseline models. Audio samples are available at http://e1tts.github.io/ .

Despite recent progress in large-scale sound event detection (SED) systems capable of handling hundreds of sound classes, existing multi-class classification frameworks remain fundamentally limited. They cannot process free-text sound queries, which enable more flexible and user-friendly interaction, and they lack zero-shot capabilities and offer poor few-shot adaptability. Although text-query-based separation methods have been explored, they primarily focus on source separation and are ill-suited for SED tasks that require precise temporal localization and efficient detection across large and diverse sound vocabularies. In this paper, we propose FlexSED, an open-vocabulary sound event detection system. FlexSED builds on a pretrained audio SSL model and the CLAP text encoder, introducing an encoder-decoder composition and an adaptive fusion strategy to enable effective continuous training from pretrained weights. To ensure robust supervision, it also employs large language models (LLMs) to assist in event query selection during training, addressing challenges related to missing labels. As a result, FlexSED achieves superior performance compared to vanilla SED models on AudioSet-Strong, while demonstrating strong zero-shot and few-shot capabilities. We release the code and pretrained models to support future research and applications based on FlexSED.

Text-to-speech (TTS) methods have shown promising results in voice cloning, but they require a large number of labeled text-speech pairs. Minimally-supervised speech synthesis decouples TTS by combining two types of discrete speech representations(semantic \& acoustic) and using two sequence-to-sequence tasks to enable training with minimal supervision. However, existing methods suffer from information redundancy and dimension explosion in semantic representation, and high-frequency waveform distortion in discrete acoustic representation. Autoregressive frameworks exhibit typical instability and uncontrollability issues. And non-autoregressive frameworks suffer from prosodic averaging caused by duration prediction models. To address these issues, we propose a minimally-supervised high-fidelity speech synthesis method, where all modules are constructed based on the diffusion models. The non-autoregressive framework enhances controllability, and the duration diffusion model enables diversified prosodic expression. Contrastive Token-Acoustic Pretraining (CTAP) is used as an intermediate semantic representation to solve the problems of information redundancy and dimension explosion in existing semantic coding methods. Mel-spectrogram is used as the acoustic representation. Both semantic and acoustic representations are predicted by continuous variable regression tasks to solve the problem of high-frequency fine-grained waveform distortion. Experimental results show that our proposed method outperforms the baseline method. We provide audio samples on our website.

In speech processing pipelines, improving the quality and intelligibility of real-world recordings is crucial. While supervised regression is the primary method for speech enhancement, audio tokenization is emerging as a promising alternative for a smooth integration with other modalities. However, research on speech enhancement using discrete representations is still limited. Previous work has mainly focused on semantic tokens, which tend to discard key acoustic details such as speaker identity. Additionally, these studies typically employ non-autoregressive models, assuming conditional independence of outputs and overlooking the potential improvements offered by autoregressive modeling. To address these gaps we: 1) conduct a comprehensive study of the performance of acoustic tokens for speech enhancement, including the effect of bitrate and noise strength; 2) introduce a novel transducer-based autoregressive architecture specifically designed for this task. Experiments on VoiceBank and Libri1Mix datasets show that acoustic tokens outperform semantic tokens in terms of preserving speaker identity, and that our autoregressive approach can further improve performance. Nevertheless, we observe that discrete representations still fall short compared to continuous ones, highlighting the need for further research in this area.

Neural HMMs are a type of neural transducer recently proposed for sequence-to-sequence modelling in text-to-speech. They combine the best features of classic statistical speech synthesis and modern neural TTS, requiring less data and fewer training updates, and are less prone to gibberish output caused by neural attention failures. In this paper, we combine neural HMM TTS with normalising flows for describing the highly non-Gaussian distribution of speech acoustics. The result is a powerful, fully probabilistic model of durations and acoustics that can be trained using exact maximum likelihood. Compared to dominant flow-based acoustic models, our approach integrates autoregression for improved modelling of long-range dependences such as utterance-level prosody. Experiments show that a system based on our proposal gives more accurate pronunciations and better subjective speech quality than comparable methods, whilst retaining the original advantages of neural HMMs. Audio examples and code are available at https://shivammehta25.github.io/OverFlow/

Non-autoregressive text to speech (TTS) models such as FastSpeech can synthesize speech significantly faster than previous autoregressive models with comparable quality. The training of FastSpeech model relies on an autoregressive teacher model for duration prediction (to provide more information as input) and knowledge distillation (to simplify the data distribution in output), which can ease the one-to-many mapping problem (i.e., multiple speech variations correspond to the same text) in TTS. However, FastSpeech has several disadvantages: 1) the teacher-student distillation pipeline is complicated and time-consuming, 2) the duration extracted from the teacher model is not accurate enough, and the target mel-spectrograms distilled from teacher model suffer from information loss due to data simplification, both of which limit the voice quality. In this paper, we propose FastSpeech 2, which addresses the issues in FastSpeech and better solves the one-to-many mapping problem in TTS by 1) directly training the model with ground-truth target instead of the simplified output from teacher, and 2) introducing more variation information of speech (e.g., pitch, energy and more accurate duration) as conditional inputs. Specifically, we extract duration, pitch and energy from speech waveform and directly take them as conditional inputs in training and use predicted values in inference. We further design FastSpeech 2s, which is the first attempt to directly generate speech waveform from text in parallel, enjoying the benefit of fully end-to-end inference. Experimental results show that 1) FastSpeech 2 achieves a 3x training speed-up over FastSpeech, and FastSpeech 2s enjoys even faster inference speed; 2) FastSpeech 2 and 2s outperform FastSpeech in voice quality, and FastSpeech 2 can even surpass autoregressive models. Audio samples are available at https://speechresearch.github.io/fastspeech2/.

In this paper, we focus on Whisper, a recent automatic speech recognition model trained with a massive 680k hour labeled speech corpus recorded in diverse conditions. We first show an interesting finding that while Whisper is very robust against real-world background sounds (e.g., music), its audio representation is actually not noise-invariant, but is instead highly correlated to non-speech sounds, indicating that Whisper recognizes speech conditioned on the noise type. With this finding, we build a unified audio tagging and speech recognition model Whisper-AT by freezing the backbone of Whisper, and training a lightweight audio tagging model on top of it. With <1% extra computational cost, Whisper-AT can recognize audio events, in addition to spoken text, in a single forward pass.

Recent advancements in audio-aware large language models (ALLMs) enable them to process and understand audio inputs. However, these models often hallucinate non-existent sound events, reducing their reliability in real-world applications. To address this, we propose LISTEN (Learning to Identify Sounds Through Extended Negative Samples), a contrastive-like training method that enhances ALLMs' ability to distinguish between present and absent sounds using synthesized data from the backbone LLM. Unlike prior approaches, our method requires no modification to LLM parameters and efficiently integrates audio representations via a lightweight adapter. Experiments show that LISTEN effectively mitigates hallucinations while maintaining impressive performance on existing audio question and reasoning benchmarks. At the same time, it is more efficient in both data and computation.

Recently, pre-trained language models (PLMs) have been increasingly adopted in spoken language understanding (SLU). However, automatic speech recognition (ASR) systems frequently produce inaccurate transcriptions, leading to noisy inputs for SLU models, which can significantly degrade their performance. To address this, our objective is to train SLU models to withstand ASR errors by exposing them to noises commonly observed in ASR systems, referred to as ASR-plausible noises. Speech noise injection (SNI) methods have pursued this objective by introducing ASR-plausible noises, but we argue that these methods are inherently biased towards specific ASR systems, or ASR-specific noises. In this work, we propose a novel and less biased augmentation method of introducing the noises that are plausible to any ASR system, by cutting off the non-causal effect of noises. Experimental results and analyses demonstrate the effectiveness of our proposed methods in enhancing the robustness and generalizability of SLU models against unseen ASR systems by introducing more diverse and plausible ASR noises in advance.

Bilingual English speakers speak English as one of their languages. Their English is of a non-native kind, and their conversations are of a code-mixed fashion. The intelligibility of a bilingual text-to-speech (TTS) system for such non-native English speakers depends on a lexicon that captures the phoneme sequence used by non-native speakers. However, due to the lack of non-native English lexicon, existing bilingual TTS systems employ native English lexicons that are widely available, in addition to their native language lexicon. Due to the inconsistency between the non-native English pronunciation in the audio and native English lexicon in the text, the intelligibility of synthesized speech in such TTS systems is significantly reduced. This paper is motivated by the knowledge that the native language of the speaker highly influences non-native English pronunciation. We propose a generic approach to obtain rules based on letter to phoneme alignment to map native English lexicon to their non-native version. The effectiveness of such mapping is studied by comparing bilingual (Indian English and Hindi) TTS systems trained with and without the proposed rules. The subjective evaluation shows that the bilingual TTS system trained with the proposed non-native English lexicon rules obtains a 6% absolute improvement in preference.

The Norwegian Parliamentary Speech Corpus (NPSC) is a speech dataset with recordings of meetings from Stortinget, the Norwegian parliament. It is the first, publicly available dataset containing unscripted, Norwegian speech designed for training of automatic speech recognition (ASR) systems. The recordings are manually transcribed and annotated with language codes and speakers, and there are detailed metadata about the speakers. The transcriptions exist in both normalized and non-normalized form, and non-standardized words are explicitly marked and annotated with standardized equivalents. To test the usefulness of this dataset, we have compared an ASR system trained on the NPSC with a baseline system trained on only manuscript-read speech. These systems were tested on an independent dataset containing spontaneous, dialectal speech. The NPSC-trained system performed significantly better, with a 22.9% relative improvement in word error rate (WER). Moreover, training on the NPSC is shown to have a "democratizing" effect in terms of dialects, as improvements are generally larger for dialects with higher WER from the baseline system.

Recently, there has been an increasing focus on audio-text cross-modal learning. However, most of the existing audio-text datasets contain only simple descriptions of sound events. Compared with classification labels, the advantages of such descriptions are significantly limited. In this paper, we first analyze the detailed information that human descriptions of audio may contain beyond sound event labels. Based on the analysis, we propose an automatic pipeline for curating audio-text pairs with rich details. Leveraging the property that sounds can be mixed and concatenated in the time domain, we control details in four aspects: temporal relationship, loudness, speaker identity, and occurrence number, in simulating audio mixtures. Corresponding details are transformed into captions by large language models. Audio-text pairs with rich details in text descriptions are thereby obtained. We validate the effectiveness of our pipeline with a small amount of simulated data, demonstrating that the simulated data enables models to learn detailed audio captioning.

Augmenting large language models (LLMs) to understand audio -- including non-speech sounds and non-verbal speech -- is critically important for diverse real-world applications of LLMs. In this paper, we propose Audio Flamingo, a novel audio language model with 1) strong audio understanding abilities, 2) the ability to quickly adapt to unseen tasks via in-context learning and retrieval, and 3) strong multi-turn dialogue abilities. We introduce a series of training techniques, architecture design, and data strategies to enhance our model with these abilities. Extensive evaluations across various audio understanding tasks confirm the efficacy of our method, setting new state-of-the-art benchmarks.

Footsteps are among the most ubiquitous sound effects in multimedia applications. There is substantial research into understanding the acoustic features and developing synthesis models for footstep sound effects. In this paper, we present a first attempt at adopting neural synthesis for this task. We implemented two GAN-based architectures and compared the results with real recordings as well as six traditional sound synthesis methods. Our architectures reached realism scores as high as recorded samples, showing encouraging results for the task at hand.

Scaling Text-to-speech (TTS) to large-scale datasets has been demonstrated as an effective method for improving the diversity and naturalness of synthesized speech. At the high level, previous large-scale TTS models can be categorized into either Auto-regressive (AR) based (e.g., VALL-E) or Non-auto-regressive (NAR) based models (e.g., NaturalSpeech 2/3). Although these works demonstrate good performance, they still have potential weaknesses. For instance, AR-based models are plagued by unstable generation quality and slow generation speed; meanwhile, some NAR-based models need phoneme-level duration alignment information, thereby increasing the complexity of data pre-processing, model design, and loss design. In this work, we build upon our previous publication by implementing a simple and efficient non-autoregressive (NAR) TTS framework, termed SimpleSpeech 2. SimpleSpeech 2 effectively combines the strengths of both autoregressive (AR) and non-autoregressive (NAR) methods, offering the following key advantages: (1) simplified data preparation; (2) straightforward model and loss design; and (3) stable, high-quality generation performance with fast inference speed. Compared to our previous publication, we present ({\romannumeral1}) a detailed analysis of the influence of speech tokenizer and noisy label for TTS performance; ({\romannumeral2}) four distinct types of sentence duration predictors; ({\romannumeral3}) a novel flow-based scalar latent transformer diffusion model. With these improvement, we show a significant improvement in generation performance and generation speed compared to our previous work and other state-of-the-art (SOTA) large-scale TTS models. Furthermore, we show that SimpleSpeech 2 can be seamlessly extended to multilingual TTS by training it on multilingual speech datasets. Demos are available on: {https://dongchaoyang.top/SimpleSpeech2\_demo/}.

Joint audio-video generation aims to synthesize synchronized multisensory content, yet current unified models struggle with fine-grained acoustic control, particularly for identity-preserving speech. Existing approaches either suffer from temporal misalignment due to cascaded generation or lack the capability to perform zero-shot voice cloning within a joint synthesis framework. In this work, we present MM-Sonate, a multimodal flow-matching framework that unifies controllable audio-video joint generation with zero-shot voice cloning capabilities. Unlike prior works that rely on coarse semantic descriptions, MM-Sonate utilizes a unified instruction-phoneme input to enforce strict linguistic and temporal alignment. To enable zero-shot voice cloning, we introduce a timbre injection mechanism that effectively decouples speaker identity from linguistic content. Furthermore, addressing the limitations of standard classifier-free guidance in multimodal settings, we propose a noise-based negative conditioning strategy that utilizes natural noise priors to significantly enhance acoustic fidelity. Empirical evaluations demonstrate that MM-Sonate establishes new state-of-the-art performance in joint generation benchmarks, significantly outperforming baselines in lip synchronization and speech intelligibility, while achieving voice cloning fidelity comparable to specialized Text-to-Speech systems.

Recent years have seen progress beyond domain-specific sound separation for speech or music towards universal sound separation for arbitrary sounds. Prior work on universal sound separation has investigated separating a target sound out of an audio mixture given a text query. Such text-queried sound separation systems provide a natural and scalable interface for specifying arbitrary target sounds. However, supervised text-queried sound separation systems require costly labeled audio-text pairs for training. Moreover, the audio provided in existing datasets is often recorded in a controlled environment, causing a considerable generalization gap to noisy audio in the wild. In this work, we aim to approach text-queried universal sound separation by using only unlabeled data. We propose to leverage the visual modality as a bridge to learn the desired audio-textual correspondence. The proposed CLIPSep model first encodes the input query into a query vector using the contrastive language-image pretraining (CLIP) model, and the query vector is then used to condition an audio separation model to separate out the target sound. While the model is trained on image-audio pairs extracted from unlabeled videos, at test time we can instead query the model with text inputs in a zero-shot setting, thanks to the joint language-image embedding learned by the CLIP model. Further, videos in the wild often contain off-screen sounds and background noise that may hinder the model from learning the desired audio-textual correspondence. To address this problem, we further propose an approach called noise invariant training for training a query-based sound separation model on noisy data. Experimental results show that the proposed models successfully learn text-queried universal sound separation using only noisy unlabeled videos, even achieving competitive performance against a supervised model in some settings.

Non-autoregressive text-to-speech (NAR-TTS) models such as FastSpeech 2 and Glow-TTS can synthesize high-quality speech from the given text in parallel. After analyzing two kinds of generative NAR-TTS models (VAE and normalizing flow), we find that: VAE is good at capturing the long-range semantics features (e.g., prosody) even with small model size but suffers from blurry and unnatural results; and normalizing flow is good at reconstructing the frequency bin-wise details but performs poorly when the number of model parameters is limited. Inspired by these observations, to generate diverse speech with natural details and rich prosody using a lightweight architecture, we propose PortaSpeech, a portable and high-quality generative text-to-speech model. Specifically, 1) to model both the prosody and mel-spectrogram details accurately, we adopt a lightweight VAE with an enhanced prior followed by a flow-based post-net with strong conditional inputs as the main architecture. 2) To further compress the model size and memory footprint, we introduce the grouped parameter sharing mechanism to the affine coupling layers in the post-net. 3) To improve the expressiveness of synthesized speech and reduce the dependency on accurate fine-grained alignment between text and speech, we propose a linguistic encoder with mixture alignment combining hard inter-word alignment and soft intra-word alignment, which explicitly extracts word-level semantic information. Experimental results show that PortaSpeech outperforms other TTS models in both voice quality and prosody modeling in terms of subjective and objective evaluation metrics, and shows only a slight performance degradation when reducing the model parameters to 6.7M (about 4x model size and 3x runtime memory compression ratio compared with FastSpeech 2). Our extensive ablation studies demonstrate that each design in PortaSpeech is effective.

Spontaneous speech has many affective and pragmatic functions that are interesting and challenging to model in TTS. However, the presence of reduced articulation, fillers, repetitions, and other disfluencies in spontaneous speech make the text and acoustics less aligned than in read speech, which is problematic for attention-based TTS. We propose a TTS architecture that can rapidly learn to speak from small and irregular datasets, while also reproducing the diversity of expressive phenomena present in spontaneous speech. Specifically, we add utterance-level prosody control to an existing neural HMM-based TTS system which is capable of stable, monotonic alignments for spontaneous speech. We objectively evaluate control accuracy and perform perceptual tests that demonstrate that prosody control does not degrade synthesis quality. To exemplify the power of combining prosody control and ecologically valid data for reproducing intricate spontaneous speech phenomena, we evaluate the system's capability of synthesizing two types of creaky voice. Audio samples are available at https://www.speech.kth.se/tts-demos/prosodic-hmm/

Environmental sounds like footsteps, keyboard typing, or dog barking carry rich information and emotional context, making them valuable for designing haptics in user applications. Existing audio-to-vibration methods, however, rely on signal-processing rules tuned for music or games and often fail to generalize across diverse sounds. To address this, we first investigated user perception of four existing audio-to-haptic algorithms, then created a data-driven model for environmental sounds. In Study 1, 34 participants rated vibrations generated by the four algorithms for 1,000 sounds, revealing no consistent algorithm preferences. Using this dataset, we trained Sound2Hap, a CNN-based autoencoder, to generate perceptually meaningful vibrations from diverse sounds with low latency. In Study 2, 15 participants rated its output higher than signal-processing baselines on both audio-vibration match and Haptic Experience Index (HXI), finding it more harmonious with diverse sounds. This work demonstrates a perceptually validated approach to audio-haptic translation, broadening the reach of sound-driven haptics.

Current expressive speech synthesis models are constrained by the limited availability of open-source datasets containing diverse nonverbal vocalizations (NVs). In this work, we introduce NonverbalTTS (NVTTS), a 17-hour open-access dataset annotated with 10 types of NVs (e.g., laughter, coughs) and 8 emotional categories. The dataset is derived from popular sources, VoxCeleb and Expresso, using automated detection followed by human validation. We propose a comprehensive pipeline that integrates automatic speech recognition (ASR), NV tagging, emotion classification, and a fusion algorithm to merge transcriptions from multiple annotators. Fine-tuning open-source text-to-speech (TTS) models on the NVTTS dataset achieves parity with closed-source systems such as CosyVoice2, as measured by both human evaluation and automatic metrics, including speaker similarity and NV fidelity. By releasing NVTTS and its accompanying annotation guidelines, we address a key bottleneck in expressive TTS research. The dataset is available at https://huggingface.co/datasets/deepvk/NonverbalTTS.

Neural waveform models such as the WaveNet are used in many recent text-to-speech systems, but the original WaveNet is quite slow in waveform generation because of its autoregressive (AR) structure. Although faster non-AR models were recently reported, they may be prohibitively complicated due to the use of a distilling training method and the blend of other disparate training criteria. This study proposes a non-AR neural source-filter waveform model that can be directly trained using spectrum-based training criteria and the stochastic gradient descent method. Given the input acoustic features, the proposed model first uses a source module to generate a sine-based excitation signal and then uses a filter module to transform the excitation signal into the output speech waveform. Our experiments demonstrated that the proposed model generated waveforms at least 100 times faster than the AR WaveNet and the quality of its synthetic speech is close to that of speech generated by the AR WaveNet. Ablation test results showed that both the sine-wave excitation signal and the spectrum-based training criteria were essential to the performance of the proposed model.

Speech produced by human vocal apparatus conveys substantial non-semantic information including the gender of the speaker, voice quality, affective state, abnormalities in the vocal apparatus etc. Such information is attributed to the properties of the voice source signal, which is usually estimated from the speech signal. However, most of the source estimation techniques depend heavily on the goodness of the model assumptions and are prone to noise. A popular alternative is to indirectly obtain the source information through the Electroglottographic (EGG) signal that measures the electrical admittance around the vocal folds using dedicated hardware. In this paper, we address the problem of estimating the EGG signal directly from the speech signal, devoid of any hardware. Sampling from the intractable conditional distribution of the EGG signal given the speech signal is accomplished through optimization of an evidence lower bound. This is constructed via minimization of the KL-divergence between the true and the approximated posteriors of a latent variable learned using a deep neural auto-encoder that serves an informative prior. We demonstrate the efficacy of the method at generating the EGG signal by conducting several experiments on datasets comprising multiple speakers, voice qualities, noise settings and speech pathologies. The proposed method is evaluated on many benchmark metrics and is found to agree with the gold standard while proving better than the state-of-the-art algorithms on a few tasks such as epoch extraction.

This paper presents a novel Dialectal Sound and Vowelization Recovery framework, designed to recognize borrowed and dialectal sounds within phonologically diverse and dialect-rich languages, that extends beyond its standard orthographic sound sets. The proposed framework utilized a quantized sequence of input with(out) continuous pretrained self-supervised representation. We show the efficacy of the pipeline using limited data for Arabic, a dialect-rich language containing more than 22 major dialects. Phonetically correct transcribed speech resources for dialectal Arabic are scarce. Therefore, we introduce ArabVoice15, a first-of-its-kind, curated test set featuring 5 hours of dialectal speech across 15 Arab countries, with phonetically accurate transcriptions, including borrowed and dialect-specific sounds. We described in detail the annotation guideline along with the analysis of the dialectal confusion pairs. Our extensive evaluation includes both subjective -- human perception tests and objective measures. Our empirical results, reported with three test sets, show that with only one and half hours of training data, our model improve character error rate by ~ 7\% in ArabVoice15 compared to the baseline.

From whirling ceiling fans to ticking clocks, the sounds that we hear subtly vary as we move through a scene. We ask whether these ambient sounds convey information about 3D scene structure and, if so, whether they provide a useful learning signal for multimodal models. To study this, we collect a dataset of paired audio and RGB-D recordings from a variety of quiet indoor scenes. We then train models that estimate the distance to nearby walls, given only audio as input. We also use these recordings to learn multimodal representations through self-supervision, by training a network to associate images with their corresponding sounds. These results suggest that ambient sound conveys a surprising amount of information about scene structure, and that it is a useful signal for learning multimodal features.

The objectives of this work are cross-modal text-audio and audio-text retrieval, in which the goal is to retrieve the audio content from a pool of candidates that best matches a given written description and vice versa. Text-audio retrieval enables users to search large databases through an intuitive interface: they simply issue free-form natural language descriptions of the sound they would like to hear. To study the tasks of text-audio and audio-text retrieval, which have received limited attention in the existing literature, we introduce three challenging new benchmarks. We first construct text-audio and audio-text retrieval benchmarks from the AudioCaps and Clotho audio captioning datasets. Additionally, we introduce the SoundDescs benchmark, which consists of paired audio and natural language descriptions for a diverse collection of sounds that are complementary to those found in AudioCaps and Clotho. We employ these three benchmarks to establish baselines for cross-modal text-audio and audio-text retrieval, where we demonstrate the benefits of pre-training on diverse audio tasks. We hope that our benchmarks will inspire further research into audio retrieval with free-form text queries. Code, audio features for all datasets used, and the SoundDescs dataset are publicly available at https://github.com/akoepke/audio-retrieval-benchmark.

Recent progress in Spoken Language Modeling has demonstrated the feasibility of learning language directly from speech. Generating speech through a pipeline that operates at the text level typically loses nuances, intonations, and non-verbal vocalizations. Modeling directly from speech opens up the path to more natural and expressive systems. On the other hand, speech-only systems tend to trail behind text-based language models in terms of their semantic abilities. We show that fine-tuning speech representation models on phoneme classification leads to more context-invariant representations, which in turn improve downstream language modeling performance.

Although Large Audio-Language Models (LALMs) deliver state-of-the-art (SOTA) performance, they frequently suffer from hallucinations, e.g. generating text not grounded in the audio input. We analyze these grounding failures and identify a distinct taxonomy: Event Omission, False Event Identity, Temporal Relation Error, and Quantitative Temporal Error. To address this, we introduce the AHA (Audio Hallucination Alignment) framework. By leveraging counterfactual hard negative mining, our pipeline constructs a high-quality preference dataset that forces models to distinguish strict acoustic evidence from linguistically plausible fabrications. Additionally, we establish AHA-Eval, a diagnostic benchmark designed to rigorously test these fine-grained temporal reasoning capabilities. We apply this data to align Qwen2.5-Omni. The resulting model, Qwen-Audio-AHA, achieves a 13.7% improvement on AHA-Eval. Crucially, this benefit generalizes beyond our diagnostic set. Our model shows substantial gains on public benchmarks, including 1.3% on MMAU-Test and 1.6% on MMAR, outperforming latest SOTA methods.

Human speech exhibits rich and flexible prosodic variations. To address the one-to-many mapping problem from text to prosody in a reasonable and flexible manner, we propose DiffStyleTTS, a multi-speaker acoustic model based on a conditional diffusion module and an improved classifier-free guidance, which hierarchically models speech prosodic features, and controls different prosodic styles to guide prosody prediction. Experiments show that our method outperforms all baselines in naturalness and achieves superior synthesis speed compared to three diffusion-based baselines. Additionally, by adjusting the guiding scale, DiffStyleTTS effectively controls the guidance intensity of the synthetic prosody.

Non-autoregressive (NAR) text-to-speech synthesis relies on length alignment between text sequences and audio representations, constraining naturalness and expressiveness. Existing methods depend on duration modeling or pseudo-alignment strategies that severely limit naturalness and computational efficiency. We propose M3-TTS, a concise and efficient NAR TTS paradigm based on multi-modal diffusion transformer (MM-DiT) architecture. M3-TTS employs joint diffusion transformer layers for cross-modal alignment, achieving stable monotonic alignment between variable-length text-speech sequences without pseudo-alignment requirements. Single diffusion transformer layers further enhance acoustic detail modeling. The framework integrates a mel-vae codec that provides 3* training acceleration. Experimental results on Seed-TTS and AISHELL-3 benchmarks demonstrate that M3-TTS achieves state-of-the-art NAR performance with the lowest word error rates (1.36\% English, 1.31\% Chinese) while maintaining competitive naturalness scores. Code and demos will be available at https://wwwwxp.github.io/M3-TTS.

Neural sequence-to-sequence TTS has achieved significantly better output quality than statistical speech synthesis using HMMs. However, neural TTS is generally not probabilistic and uses non-monotonic attention. Attention failures increase training time and can make synthesis babble incoherently. This paper describes how the old and new paradigms can be combined to obtain the advantages of both worlds, by replacing attention in neural TTS with an autoregressive left-right no-skip hidden Markov model defined by a neural network. Based on this proposal, we modify Tacotron 2 to obtain an HMM-based neural TTS model with monotonic alignment, trained to maximise the full sequence likelihood without approximation. We also describe how to combine ideas from classical and contemporary TTS for best results. The resulting example system is smaller and simpler than Tacotron 2, and learns to speak with fewer iterations and less data, whilst achieving comparable naturalness prior to the post-net. Our approach also allows easy control over speaking rate.

We introduce Seed-TTS, a family of large-scale autoregressive text-to-speech (TTS) models capable of generating speech that is virtually indistinguishable from human speech. Seed-TTS serves as a foundation model for speech generation and excels in speech in-context learning, achieving performance in speaker similarity and naturalness that matches ground truth human speech in both objective and subjective evaluations. With fine-tuning, we achieve even higher subjective scores across these metrics. Seed-TTS offers superior controllability over various speech attributes such as emotion and is capable of generating highly expressive and diverse speech for speakers in the wild. Furthermore, we propose a self-distillation method for speech factorization, as well as a reinforcement learning approach to enhance model robustness, speaker similarity, and controllability. We additionally present a non-autoregressive (NAR) variant of the Seed-TTS model, named Seed-TTS_DiT, which utilizes a fully diffusion-based architecture. Unlike previous NAR-based TTS systems, Seed-TTS_DiT does not depend on pre-estimated phoneme durations and performs speech generation through end-to-end processing. We demonstrate that this variant achieves comparable performance to the language model-based variant and showcase its effectiveness in speech editing. We encourage readers to listen to demos at https://bytedancespeech.github.io/seedtts_tech_report.

The recent large-scale text-to-speech (TTS) systems are usually grouped as autoregressive and non-autoregressive systems. The autoregressive systems implicitly model duration but exhibit certain deficiencies in robustness and lack of duration controllability. Non-autoregressive systems require explicit alignment information between text and speech during training and predict durations for linguistic units (e.g. phone), which may compromise their naturalness. In this paper, we introduce Masked Generative Codec Transformer (MaskGCT), a fully non-autoregressive TTS model that eliminates the need for explicit alignment information between text and speech supervision, as well as phone-level duration prediction. MaskGCT is a two-stage model: in the first stage, the model uses text to predict semantic tokens extracted from a speech self-supervised learning (SSL) model, and in the second stage, the model predicts acoustic tokens conditioned on these semantic tokens. MaskGCT follows the mask-and-predict learning paradigm. During training, MaskGCT learns to predict masked semantic or acoustic tokens based on given conditions and prompts. During inference, the model generates tokens of a specified length in a parallel manner. Experiments with 100K hours of in-the-wild speech demonstrate that MaskGCT outperforms the current state-of-the-art zero-shot TTS systems in terms of quality, similarity, and intelligibility. Audio samples are available at https://maskgct.github.io/.

The task of Visual Sound Source Localization (VSSL) involves identifying the location of sound sources in visual scenes, integrating audio-visual data for enhanced scene understanding. Despite advancements in state-of-the-art (SOTA) models, we observe three critical flaws: i) The evaluation of the models is mainly focused in sounds produced by objects that are visible in the image, ii) The evaluation often assumes a prior knowledge of the size of the sounding object, and iii) No universal threshold for localization in real-world scenarios is established, as previous approaches only consider positive examples without accounting for both positive and negative cases. In this paper, we introduce a novel test set and metrics designed to complete the current standard evaluation of VSSL models by testing them in scenarios where none of the objects in the image corresponds to the audio input, i.e. a negative audio. We consider three types of negative audio: silence, noise and offscreen. Our analysis reveals that numerous SOTA models fail to appropriately adjust their predictions based on audio input, suggesting that these models may not be leveraging audio information as intended. Additionally, we provide a comprehensive analysis of the range of maximum values in the estimated audio-visual similarity maps, in both positive and negative audio cases, and show that most of the models are not discriminative enough, making them unfit to choose a universal threshold appropriate to perform sound localization without any a priori information of the sounding object, that is, object size and visibility.

Semantic information refers to the meaning conveyed through words, phrases, and contextual relationships within a given linguistic structure. Humans can leverage semantic information, such as familiar linguistic patterns and contextual cues, to reconstruct incomplete or masked speech signals in noisy environments. However, existing speech enhancement (SE) approaches often overlook the rich semantic information embedded in speech, which is crucial for improving intelligibility, speaker consistency, and overall quality of enhanced speech signals. To enrich the SE model with semantic information, we employ language models as an efficient semantic learner and propose a comprehensive framework tailored for language model-based speech enhancement, called GenSE. Specifically, we approach SE as a conditional language modeling task rather than a continuous signal regression problem defined in existing works. This is achieved by tokenizing speech signals into semantic tokens using a pre-trained self-supervised model and into acoustic tokens using a custom-designed single-quantizer neural codec model. To improve the stability of language model predictions, we propose a hierarchical modeling method that decouples the generation of clean semantic tokens and clean acoustic tokens into two distinct stages. Moreover, we introduce a token chain prompting mechanism during the acoustic token generation stage to ensure timbre consistency throughout the speech enhancement process. Experimental results on benchmark datasets demonstrate that our proposed approach outperforms state-of-the-art SE systems in terms of speech quality and generalization capability.

Perceiving and understanding non-speech sounds and non-verbal speech is essential to making decisions that help us interact with our surroundings. In this paper, we propose GAMA, a novel General-purpose Large Audio-Language Model (LALM) with Advanced Audio Understanding and Complex Reasoning Abilities. We build GAMA by integrating an LLM with multiple types of audio representations, including features from a custom Audio Q-Former, a multi-layer aggregator that aggregates features from multiple layers of an audio encoder. We fine-tune GAMA on a large-scale audio-language dataset, which augments it with audio understanding capabilities. Next, we propose CompA-R (Instruction-Tuning for Complex Audio Reasoning), a synthetically generated instruction-tuning (IT) dataset with instructions that require the model to perform complex reasoning on the input audio. We instruction-tune GAMA with CompA-R to endow it with complex reasoning abilities, where we further add a soft prompt as input with high-level semantic evidence by leveraging event tags of the input audio. Finally, we also propose CompA-R-test, a human-labeled evaluation dataset for evaluating the capabilities of LALMs on open-ended audio question-answering that requires complex reasoning. Through automated and expert human evaluations, we show that GAMA outperforms all other LALMs in literature on diverse audio understanding tasks by margins of 1%-84%. Further, GAMA IT-ed on CompA-R proves to be superior in its complex reasoning and instruction following capabilities.

Transformer-based self-supervised speech models (S3Ms) are often described as contextualized, yet what this entails remains unclear. Here, we focus on how a single frame-level S3M representation can encode phones and their surrounding context. Prior work has shown that S3Ms represent phones compositionally; for example, phonological vectors such as voicing, bilabiality, and nasality vectors are superposed in the S3M representation of [m]. We extend this view by proposing that phonological information from a sequence of neighboring phones is also compositionally encoded in a single frame, such that vectors corresponding to previous, current, and next phones are superposed within a single frame-level representation. We show that this structure has several properties, including orthogonality between relative positions, and emergence of implicit phonetic boundaries. Together, our findings advance our understanding of context-dependent S3M representations.

Recent advancements in visual speech recognition (VSR) have promoted progress in lip-to-speech synthesis, where pre-trained VSR models enhance the intelligibility of synthesized speech by providing valuable semantic information. The success achieved by cascade frameworks, which combine pseudo-VSR with pseudo-text-to-speech (TTS) or implicitly utilize the transcribed text, highlights the benefits of leveraging VSR models. However, these methods typically rely on mel-spectrograms as an intermediate representation, which may introduce a key bottleneck: the domain gap between synthetic mel-spectrograms, generated from inherently error-prone lip-to-speech mappings, and real mel-spectrograms used to train vocoders. This mismatch inevitably degrades synthesis quality. To bridge this gap, we propose Natural Lip-to-Speech (NaturalL2S), an end-to-end framework integrating acoustic inductive biases with differentiable speech generation components. Specifically, we introduce a fundamental frequency (F0) predictor to capture prosodic variations in synthesized speech. The predicted F0 then drives a Differentiable Digital Signal Processing (DDSP) synthesizer to generate a coarse signal which serves as prior information for subsequent speech synthesis. Additionally, instead of relying on a reference speaker embedding as an auxiliary input, our approach achieves satisfactory performance on speaker similarity without explicitly modelling speaker characteristics. Both objective and subjective evaluation results demonstrate that NaturalL2S can effectively enhance the quality of the synthesized speech when compared to state-of-the-art methods. Our demonstration page is accessible at https://yifan-liang.github.io/NaturalL2S/.

There has been a growing interest in the task of generating sound for silent videos, primarily because of its practicality in streamlining video post-production. However, existing methods for video-sound generation attempt to directly create sound from visual representations, which can be challenging due to the difficulty of aligning visual representations with audio representations. In this paper, we present SonicVisionLM, a novel framework aimed at generating a wide range of sound effects by leveraging vision-language models(VLMs). Instead of generating audio directly from video, we use the capabilities of powerful VLMs. When provided with a silent video, our approach first identifies events within the video using a VLM to suggest possible sounds that match the video content. This shift in approach transforms the challenging task of aligning image and audio into more well-studied sub-problems of aligning image-to-text and text-to-audio through the popular diffusion models. To improve the quality of audio recommendations with LLMs, we have collected an extensive dataset that maps text descriptions to specific sound effects and developed a time-controlled audio adapter. Our approach surpasses current state-of-the-art methods for converting video to audio, enhancing synchronization with the visuals, and improving alignment between audio and video components. Project page: https://yusiissy.github.io/SonicVisionLM.github.io/

In this paper, we present a 170.83 hour Indian English spontaneous speech dataset. Lack of Indian English speech data is one of the major hindrances in developing robust speech systems which are adapted to the Indian speech style. Moreover this scarcity is even more for spontaneous speech. This corpus is crowd sourced over varied Indian nativities, genders and age groups. Traditional spontaneous speech collection strategies involve capturing of speech during interviewing or conversations. In this study, we use images as stimuli to induce spontaneity in speech. Transcripts for 23 hours is generated and validated which can serve as a spontaneous speech ASR benchmark. Quality of the corpus is validated with voice activity detection based segmentation, gender verification and image semantic correlation. Which determines a relationship between image stimulus and recorded speech using caption keywords derived from Image2Text model and high occurring words derived from whisper ASR generated transcripts.

Spatial sound reasoning is a fundamental human skill, enabling us to navigate and interpret our surroundings based on sound. In this paper we present BAT, which combines the spatial sound perception ability of a binaural acoustic scene analysis model with the natural language reasoning capabilities of a large language model (LLM) to replicate this innate ability. To address the lack of existing datasets of in-the-wild spatial sounds, we synthesized a binaural audio dataset using AudioSet and SoundSpaces 2.0. Next, we developed SpatialSoundQA, a spatial sound-based question-answering dataset, offering a range of QA tasks that train BAT in various aspects of spatial sound perception and reasoning. The acoustic front end encoder of BAT is a novel spatial audio encoder named Spatial Audio Spectrogram Transformer, or Spatial-AST, which by itself achieves strong performance across sound event detection, spatial localization, and distance estimation. By integrating Spatial-AST with LLaMA-2 7B model, BAT transcends standard Sound Event Localization and Detection (SELD) tasks, enabling the model to reason about the relationships between the sounds in its environment. Our experiments demonstrate BAT's superior performance on both spatial sound perception and reasoning, showcasing the immense potential of LLMs in navigating and interpreting complex spatial audio environments.

We introduce the first Natural Office Talkers in Settings of Far-field Audio Recordings (``NOTSOFAR-1'') Challenge alongside datasets and baseline system. The challenge focuses on distant speaker diarization and automatic speech recognition (DASR) in far-field meeting scenarios, with single-channel and known-geometry multi-channel tracks, and serves as a launch platform for two new datasets: First, a benchmarking dataset of 315 meetings, averaging 6 minutes each, capturing a broad spectrum of real-world acoustic conditions and conversational dynamics. It is recorded across 30 conference rooms, featuring 4-8 attendees and a total of 35 unique speakers. Second, a 1000-hour simulated training dataset, synthesized with enhanced authenticity for real-world generalization, incorporating 15,000 real acoustic transfer functions. The tasks focus on single-device DASR, where multi-channel devices always share the same known geometry. This is aligned with common setups in actual conference rooms, and avoids technical complexities associated with multi-device tasks. It also allows for the development of geometry-specific solutions. The NOTSOFAR-1 Challenge aims to advance research in the field of distant conversational speech recognition, providing key resources to unlock the potential of data-driven methods, which we believe are currently constrained by the absence of comprehensive high-quality training and benchmarking datasets.

Speechreading is a notoriously difficult task for humans to perform. In this paper we present an end-to-end model based on a convolutional neural network (CNN) for generating an intelligible acoustic speech signal from silent video frames of a speaking person. The proposed CNN generates sound features for each frame based on its neighboring frames. Waveforms are then synthesized from the learned speech features to produce intelligible speech. We show that by leveraging the automatic feature learning capabilities of a CNN, we can obtain state-of-the-art word intelligibility on the GRID dataset, and show promising results for learning out-of-vocabulary (OOV) words.

Non-autoregressive (NAR) modeling has gained significant interest in speech processing since these models achieve dramatically lower inference time than autoregressive (AR) models while also achieving good transcription accuracy. Since NAR automatic speech recognition (ASR) models must wait for the completion of the entire utterance before processing, some works explore streaming NAR models based on blockwise attention for low-latency applications. However, streaming NAR models significantly lag in accuracy compared to streaming AR and non-streaming NAR models. To address this, we propose a streaming "semi-autoregressive" ASR model that incorporates the labels emitted in previous blocks as additional context using a Language Model (LM) subnetwork. We also introduce a novel greedy decoding algorithm that addresses insertion and deletion errors near block boundaries while not significantly increasing the inference time. Experiments show that our method outperforms the existing streaming NAR model by 19% relative on Tedlium2, 16%/8% on Librispeech-100 clean/other test sets, and 19%/8% on the Switchboard(SWB) / Callhome(CH) test sets. It also reduced the accuracy gap with streaming AR and non-streaming NAR models while achieving 2.5x lower latency. We also demonstrate that our approach can effectively utilize external text data to pre-train the LM subnetwork to further improve streaming ASR accuracy.

Speaker anonymization (SA) systems modify timbre while leaving regional or non-native accents intact, which is problematic because accents can narrow the anonymity set. To address this issue, we present PHONOS, a streaming module for real-time SA that neutralizes non-native accent to sound native-like. Our approach pre-generates golden speaker utterances that preserve source timbre and rhythm but replace foreign segmentals with native ones using silence-aware DTW alignment and zero-shot voice conversion. These utterances supervise a causal accent translator that maps non-native content tokens to native equivalents with at most 40ms look-ahead, trained using joint cross-entropy and CTC losses. Our evaluations show an 81% reduction in non-native accent confidence, with listening-test ratings consistent with this shift, and reduced speaker linkability as accent-neutralized utterances move away from the original speaker in embedding space while having latency under 241 ms on single GPU.

We tackle the task of text-to-speech (TTS) in Hebrew. Traditional Hebrew contains Diacritics, which dictate the way individuals should pronounce given words, however, modern Hebrew rarely uses them. The lack of diacritics in modern Hebrew results in readers expected to conclude the correct pronunciation and understand which phonemes to use based on the context. This imposes a fundamental challenge on TTS systems to accurately map between text-to-speech. In this work, we propose to adopt a language modeling Diacritics-Free approach, for the task of Hebrew TTS. The model operates on discrete speech representations and is conditioned on a word-piece tokenizer. We optimize the proposed method using in-the-wild weakly supervised data and compare it to several diacritic-based TTS systems. Results suggest the proposed method is superior to the evaluated baselines considering both content preservation and naturalness of the generated speech. Samples can be found under the following link: pages.cs.huji.ac.il/adiyoss-lab/HebTTS/

Self-supervised learning (SSL) models use only the intrinsic structure of a given signal, independent of its acoustic domain, to extract essential information from the input to an embedding space. This implies that the utility of such representations is not limited to modeling human speech alone. Building on this understanding, this paper explores the cross-transferability of SSL neural representations learned from human speech to analyze bio-acoustic signals. We conduct a caller discrimination analysis and a caller detection study on Marmoset vocalizations using eleven SSL models pre-trained with various pretext tasks. The results show that the embedding spaces carry meaningful caller information and can successfully distinguish the individual identities of Marmoset callers without fine-tuning. This demonstrates that representations pre-trained on human speech can be effectively applied to the bio-acoustics domain, providing valuable insights for future investigations in this field.

Text to speech (TTS) has been broadly used to synthesize natural and intelligible speech in different scenarios. Deploying TTS in various end devices such as mobile phones or embedded devices requires extremely small memory usage and inference latency. While non-autoregressive TTS models such as FastSpeech have achieved significantly faster inference speed than autoregressive models, their model size and inference latency are still large for the deployment in resource constrained devices. In this paper, we propose LightSpeech, which leverages neural architecture search~(NAS) to automatically design more lightweight and efficient models based on FastSpeech. We first profile the components of current FastSpeech model and carefully design a novel search space containing various lightweight and potentially effective architectures. Then NAS is utilized to automatically discover well performing architectures within the search space. Experiments show that the model discovered by our method achieves 15x model compression ratio and 6.5x inference speedup on CPU with on par voice quality. Audio demos are provided at https://speechresearch.github.io/lightspeech.

This paper explores a novel perspective to speech quality assessment by leveraging natural language descriptions, offering richer, more nuanced insights than traditional numerical scoring methods. Natural language feedback provides instructive recommendations and detailed evaluations, yet existing datasets lack the comprehensive annotations needed for this approach. To bridge this gap, we introduce QualiSpeech, a comprehensive low-level speech quality assessment dataset encompassing 11 key aspects and detailed natural language comments that include reasoning and contextual insights. Additionally, we propose the QualiSpeech Benchmark to evaluate the low-level speech understanding capabilities of auditory large language models (LLMs). Experimental results demonstrate that finetuned auditory LLMs can reliably generate detailed descriptions of noise and distortion, effectively identifying their types and temporal characteristics. The results further highlight the potential for incorporating reasoning to enhance the accuracy and reliability of quality assessments. The dataset will be released at https://huggingface.co/datasets/tsinghua-ee/QualiSpeech.

Neural audio synthesis methods now allow specifying ideas in natural language. However, these methods produce results that cannot be easily tweaked, as they are based on large latent spaces and up to billions of uninterpretable parameters. We propose a text-to-audio generation method that leverages a virtual modular sound synthesizer with only 78 parameters. Synthesizers have long been used by skilled sound designers for media like music and film due to their flexibility and intuitive controls. Our method, CTAG, iteratively updates a synthesizer's parameters to produce high-quality audio renderings of text prompts that can be easily inspected and tweaked. Sounds produced this way are also more abstract, capturing essential conceptual features over fine-grained acoustic details, akin to how simple sketches can vividly convey visual concepts. Our results show how CTAG produces sounds that are distinctive, perceived as artistic, and yet similarly identifiable to recent neural audio synthesis models, positioning it as a valuable and complementary tool.

Large Language Models (LLMs) have recently garnered significant attention, primarily for their capabilities in text-based interactions. However, natural human interaction often relies on speech, necessitating a shift towards voice-based models. A straightforward approach to achieve this involves a pipeline of ``Automatic Speech Recognition (ASR) + LLM + Text-to-Speech (TTS)", where input speech is transcribed to text, processed by an LLM, and then converted back to speech. Despite being straightforward, this method suffers from inherent limitations, such as information loss during modality conversion and error accumulation across the three stages. To address these issues, Speech Language Models (SpeechLMs) -- end-to-end models that generate speech without converting from text -- have emerged as a promising alternative. This survey paper provides the first comprehensive overview of recent methodologies for constructing SpeechLMs, detailing the key components of their architecture and the various training recipes integral to their development. Additionally, we systematically survey the various capabilities of SpeechLMs, categorize the evaluation metrics for SpeechLMs, and discuss the challenges and future research directions in this rapidly evolving field.

Automatic Speech Recognition (ASR) systems convert speech into text and can be placed into two broad categories: traditional and fully end-to-end. Both types have been shown to be vulnerable to adversarial audio examples that sound benign to the human ear but force the ASR to produce malicious transcriptions. Of these attacks, only the "psychoacoustic" attacks can create examples with relatively imperceptible perturbations, as they leverage the knowledge of the human auditory system. Unfortunately, existing psychoacoustic attacks can only be applied against traditional models, and are obsolete against the newer, fully end-to-end ASRs. In this paper, we propose an equalization-based psychoacoustic attack that can exploit both traditional and fully end-to-end ASRs. We successfully demonstrate our attack against real-world ASRs that include DeepSpeech and Wav2Letter. Moreover, we employ a user study to verify that our method creates low audible distortion. Specifically, 80 of the 100 participants voted in favor of all our attack audio samples as less noisier than the existing state-of-the-art attack. Through this, we demonstrate both types of existing ASR pipelines can be exploited with minimum degradation to attack audio quality.

In recent years, several text-to-speech systems have been proposed to synthesize natural speech in zero-shot, few-shot, and low-resource scenarios. However, these methods typically require training with data from many different speakers. The speech quality across the speaker set typically is diverse and imposes an upper limit on the quality achievable for the low-resource speaker. In the current work, we achieve high-quality speech synthesis using as little as five minutes of speech from the desired speaker by augmenting the low-resource speaker data with noise and employing multiple sampling techniques during training. Our method requires only four high-quality, high-resource speakers, which are easy to obtain and use in practice. Our low-complexity method achieves improved speaker similarity compared to the state-of-the-art zero-shot method HierSpeech++ and the recent low-resource method AdapterMix while maintaining comparable naturalness. Our proposed approach can also reduce the data requirements for speech synthesis for new speakers and languages.

Large audio-language models are advancing rapidly, yet most evaluations emphasize speech or globally sourced sounds, overlooking culturally distinctive cues. This gap raises a critical question: can current models generalize to localized, non-semantic audio that communities instantly recognize but outsiders do not? To address this, we present TAU (Taiwan Audio Understanding), a benchmark of everyday Taiwanese "soundmarks." TAU is built through a pipeline combining curated sources, human editing, and LLM-assisted question generation, producing 702 clips and 1,794 multiple-choice items that cannot be solved by transcripts alone. Experiments show that state-of-the-art LALMs, including Gemini 2.5 and Qwen2-Audio, perform far below local humans. TAU demonstrates the need for localized benchmarks to reveal cultural blind spots, guide more equitable multimodal evaluation, and ensure models serve communities beyond the global mainstream.

Scaling text-to-speech (TTS) to large-scale, multi-speaker, and in-the-wild datasets is important to capture the diversity in human speech such as speaker identities, prosodies, and styles (e.g., singing). Current large TTS systems usually quantize speech into discrete tokens and use language models to generate these tokens one by one, which suffer from unstable prosody, word skipping/repeating issue, and poor voice quality. In this paper, we develop NaturalSpeech 2, a TTS system that leverages a neural audio codec with residual vector quantizers to get the quantized latent vectors and uses a diffusion model to generate these latent vectors conditioned on text input. To enhance the zero-shot capability that is important to achieve diverse speech synthesis, we design a speech prompting mechanism to facilitate in-context learning in the diffusion model and the duration/pitch predictor. We scale NaturalSpeech 2 to large-scale datasets with 44K hours of speech and singing data and evaluate its voice quality on unseen speakers. NaturalSpeech 2 outperforms previous TTS systems by a large margin in terms of prosody/timbre similarity, robustness, and voice quality in a zero-shot setting, and performs novel zero-shot singing synthesis with only a speech prompt. Audio samples are available at https://speechresearch.github.io/naturalspeech2.

In the past, the rapidly evolving field of sound classification greatly benefited from the application of methods from other domains. Today, we observe the trend to fuse domain-specific tasks and approaches together, which provides the community with new outstanding models. In this work, we present an extension of the CLIP model that handles audio in addition to text and images. Our proposed model incorporates the ESResNeXt audio-model into the CLIP framework using the AudioSet dataset. Such a combination enables the proposed model to perform bimodal and unimodal classification and querying, while keeping CLIP's ability to generalize to unseen datasets in a zero-shot inference fashion. AudioCLIP achieves new state-of-the-art results in the Environmental Sound Classification (ESC) task, out-performing other approaches by reaching accuracies of 90.07% on the UrbanSound8K and 97.15% on the ESC-50 datasets. Further it sets new baselines in the zero-shot ESC-task on the same datasets (68.78% and 69.40%, respectively). Finally, we also assess the cross-modal querying performance of the proposed model as well as the influence of full and partial training on the results. For the sake of reproducibility, our code is published.

Current speech generation research can be categorized into two primary classes: non-autoregressive and autoregressive. The fundamental distinction between these approaches lies in the duration prediction strategy employed for predictable-length sequences. The NAR methods ensure stability in speech generation by explicitly and independently modeling the duration of each phonetic unit. Conversely, AR methods employ an autoregressive paradigm to predict the compressed speech token by implicitly modeling duration with Markov properties. Although this approach improves prosody, it does not provide the structural guarantees necessary for stability. To simultaneously address the issues of stability and naturalness in speech generation, we propose FlexSpeech, a stable, controllable, and expressive TTS model. The motivation behind FlexSpeech is to incorporate Markov dependencies and preference optimization directly on the duration predictor to boost its naturalness while maintaining explicit modeling of the phonetic units to ensure stability. Specifically, we decompose the speech generation task into two components: an AR duration predictor and a NAR acoustic model. The acoustic model is trained on a substantial amount of data to learn to render audio more stably, given reference audio prosody and phone durations. The duration predictor is optimized in a lightweight manner for different stylistic variations, thereby enabling rapid style transfer while maintaining a decoupled relationship with the specified speaker timbre. Experimental results demonstrate that our approach achieves SOTA stability and naturalness in zero-shot TTS. More importantly, when transferring to a specific stylistic domain, we can accomplish lightweight optimization of the duration module solely with about 100 data samples, without the need to adjust the acoustic model, thereby enabling rapid and stable style transfer.

We present a unified system to realize one-shot voice conversion (VC) on the pitch, rhythm, and speaker attributes. Existing works generally ignore the correlation between prosody and language content, leading to the degradation of naturalness in converted speech. Additionally, the lack of proper language features prevents these systems from accurately preserving language content after conversion. To address these issues, we devise a cascaded modular system leveraging self-supervised discrete speech units as language representation. These discrete units provide duration information essential for rhythm modeling. Our system first extracts utterance-level prosody and speaker representations from the raw waveform. Given the prosody representation, a prosody predictor estimates pitch, energy, and duration for each discrete unit in the utterance. A synthesizer further reconstructs speech based on the predicted prosody, speaker representation, and discrete units. Experiments show that our system outperforms previous approaches in naturalness, intelligibility, speaker transferability, and prosody transferability. Code and samples are publicly available.

Contrastive language-audio pretraining (CLAP) has recently emerged as a method for making audio analysis more generalisable. Specifically, CLAP-style models are able to `answer' a diverse set of language queries, extending the capabilities of audio models beyond a closed set of labels. However, CLAP relies on a large set of (audio, query) pairs for pretraining. While such sets are available for general audio tasks, like captioning or sound event detection, there are no datasets with matched audio and text queries for computational paralinguistic (CP) tasks. As a result, the community relies on generic CLAP models trained for general audio with limited success. In the present study, we explore training considerations for ParaCLAP, a CLAP-style model suited to CP, including a novel process for creating audio-language queries. We demonstrate its effectiveness on a set of computational paralinguistic tasks, where it is shown to surpass the performance of open-source state-of-the-art models.

We present a multi-speaker Japanese audiobook text-to-speech (TTS) system that leverages multimodal context information of preceding acoustic context and bilateral textual context to improve the prosody of synthetic speech. Previous work either uses unilateral or single-modality context, which does not fully represent the context information. The proposed method uses an acoustic context encoder and a textual context encoder to aggregate context information and feeds it to the TTS model, which enables the model to predict context-dependent prosody. We conducted comprehensive objective and subjective evaluations on a multi-speaker Japanese audiobook dataset. Experimental results demonstrate that the proposed method significantly outperforms two previous works. Additionally, we present insights about the different choices of context - modalities, lateral information and length - for audiobook TTS that have never been discussed in the literature before.

Large audio-video language models can generate descriptions for both video and audio. However, they sometimes ignore audio content, producing audio descriptions solely reliant on visual information. This paper refers to this as audio hallucinations and analyzes them in large audio-video language models. We gather 1,000 sentences by inquiring about audio information and annotate them whether they contain hallucinations. If a sentence is hallucinated, we also categorize the type of hallucination. The results reveal that 332 sentences are hallucinated with distinct trends observed in nouns and verbs for each hallucination type. Based on this, we tackle a task of audio hallucination classification using pre-trained audio-text models in the zero-shot and fine-tuning settings. Our experimental results reveal that the zero-shot models achieve higher performance (52.2% in F1) than the random (40.3%) and the fine-tuning models achieve 87.9%, outperforming the zero-shot models.

This paper presents a new approach to fine-tuning OpenAI's Whisper model for low-resource languages by introducing a novel data generation method that converts sentence-level data into a long-form corpus, using Swiss German as a case study. Non-sentence-level data, which could improve the performance of long-form audio, is difficult to obtain and often restricted by copyright laws. Our method bridges this gap by transforming more accessible sentence-level data into a format that preserves the model's ability to handle long-form audio and perform segmentation without requiring non-sentence-level data. Our data generation process improves performance in several real-world applications and leads to the development of a new state-of-the-art speech-to-text (STT) model for Swiss German. We compare our model with a non-fine-tuned Whisper and our previous state-of-the-art Swiss German STT models, where our new model achieves higher BLEU scores. Our results also indicate that the proposed method is adaptable to other low-resource languages, supported by written guidance and code that allows the creation of fine-tuned Whisper models, which keep segmentation capabilities and allow the transcription of longer audio files using only sentence-level data with high quality.

Text-to-Speech (TTS) models can generate natural, human-like speech across multiple languages by transforming phonemes into waveforms. However, multilingual TTS remains challenging due to discrepancies in phoneme vocabularies and variations in prosody and speaking style across languages. Existing approaches either train separate models for each language, which achieve high performance at the cost of increased computational resources, or use a unified model for multiple languages that struggles to capture fine-grained, language-specific style variations. In this work, we propose LanStyleTTS, a non-autoregressive, language-aware style adaptive TTS framework that standardizes phoneme representations and enables fine-grained, phoneme-level style control across languages. This design supports a unified multilingual TTS model capable of producing accurate and high-quality speech without the need to train language-specific models. We evaluate LanStyleTTS by integrating it with several state-of-the-art non-autoregressive TTS architectures. Results show consistent performance improvements across different model backbones. Furthermore, we investigate a range of acoustic feature representations, including mel-spectrograms and autoencoder-derived latent features. Our experiments demonstrate that latent encodings can significantly reduce model size and computational cost while preserving high-quality speech generation.

Large language models (LLMs) prompted with text and audio represent the state of the art in various auditory tasks, including speech, music, and general audio, showing emergent abilities on unseen tasks. However, these capabilities have yet to be fully demonstrated in bioacoustics tasks, such as detecting animal vocalizations in large recordings, classifying rare and endangered species, and labeling context and behavior - tasks that are crucial for conservation, biodiversity monitoring, and the study of animal behavior. In this work, we present NatureLM-audio, the first audio-language foundation model specifically designed for bioacoustics. Our carefully curated training dataset comprises text-audio pairs spanning a diverse range of bioacoustics, speech, and music data, designed to address the challenges posed by limited annotated datasets in the field. We demonstrate successful transfer of learned representations from music and speech to bioacoustics, and our model shows promising generalization to unseen taxa and tasks. Importantly, we test NatureLM-audio on a novel benchmark (BEANS-Zero) and it sets the new state of the art (SotA) on several bioacoustics tasks, including zero-shot classification of unseen species. To advance bioacoustics research, we also open-source the code for generating training and benchmark data, as well as for training the model.

Voice conversion refers to transferring speaker identity with well-preserved content. Better disentanglement of speech representations leads to better voice conversion. Recent studies have found that phonetic information from input audio has the potential ability to well represent content. Besides, the speaker-style modeling with pre-trained models making the process more complex. To tackle these issues, we introduce a new method named "CTVC" which utilizes disentangled speech representations with contrastive learning and time-invariant retrieval. Specifically, a similarity-based compression module is used to facilitate a more intimate connection between the frame-level hidden features and linguistic information at phoneme-level. Additionally, a time-invariant retrieval is proposed for timbre extraction based on multiple segmentations and mutual information. Experimental results demonstrate that "CTVC" outperforms previous studies and improves the sound quality and similarity of converted results.

An important problem in machine auditory perception is to recognize and detect sound events. In this paper, we propose a sequential self-teaching approach to learning sounds. Our main proposition is that it is harder to learn sounds in adverse situations such as from weakly labeled and/or noisy labeled data, and in these situations a single stage of learning is not sufficient. Our proposal is a sequential stage-wise learning process that improves generalization capabilities of a given modeling system. We justify this method via technical results and on Audioset, the largest sound events dataset, our sequential learning approach can lead to up to 9% improvement in performance. A comprehensive evaluation also shows that the method leads to improved transferability of knowledge from previously trained models, thereby leading to improved generalization capabilities on transfer learning tasks.

Audio chaptering, the task of automatically segmenting long-form audio into coherent sections, is increasingly important for navigating podcasts, lectures, and videos. Despite its relevance, research remains limited and text-based, leaving key questions unresolved about leveraging audio information, handling ASR errors, and transcript-free evaluation. We address these gaps through three contributions: (1) a systematic comparison between text-based models with acoustic features, a novel audio-only architecture (AudioSeg) operating on learned audio representations, and multimodal LLMs; (2) empirical analysis of factors affecting performance, including transcript quality, acoustic features, duration, and speaker composition; and (3) formalized evaluation protocols contrasting transcript-dependent text-space protocols with transcript-invariant time-space protocols. Our experiments on YTSeg reveal that AudioSeg substantially outperforms text-based approaches, pauses provide the largest acoustic gains, and MLLMs remain limited by context length and weak instruction following, yet MLLMs are promising on shorter audio.

Although audio foundations models have seen great progress on a wide variety of tasks, their application in real-world acoustic environments with reverberation and noise has been less successful. Moreover, as audio foundation models are typically trained on dry, single-channel audio clips, the inherent spatial nature of real-world sound scenes is overlooked and tasks involving sound localization ruled out. To address these limitations, we propose GRAM: a General-purpose Real-world Audio Model utilizing a multi-channel masked auto-encoder approach to efficiently learn spatial audio representations from high-quality simulated real-world scenes. To evaluate the performance of GRAM and other audio foundation models in real-world sound scenes, we release Nat-HEAR: A naturalistic version of the HEAR benchmark suite comprising a simulated real-world version, as well as two new sound localization tasks. We show that the performance of GRAM surpasses all state-of-the-art self-supervised audio foundation models and speech models on both HEAR and Nat-HEAR, while using only a fraction of the training data. GRAM also showcases state-of-the-art localization performance, surpassing even supervised sound localization approaches, and can be flexibly applied either to a two-channel, binaural sound format or a four-channel, Ambisonics format. Validating GRAM's performance on real-world sound recordings demonstrates robust transfer to real-world scenes. Taken together, GRAM presents a significant advancement towards robust, spatial audio foundation models for real-world applications.

Accurate audio quality estimation is essential for developing and evaluating audio generation, retrieval, and enhancement systems. Existing non-intrusive assessment models predict a single Mean Opinion Score (MOS) for speech, merging diverse perceptual factors and failing to generalize beyond speech. We propose MMMOS, a no-reference, multi-domain audio quality assessment system that estimates four orthogonal axes: Production Quality, Production Complexity, Content Enjoyment, and Content Usefulness across speech, music, and environmental sounds. MMMOS fuses frame-level embeddings from three pretrained encoders (WavLM, MuQ, and M2D) and evaluates three aggregation strategies with four loss functions. By ensembling the top eight models, MMMOS shows a 20-30% reduction in mean squared error and a 4-5% increase in Kendall's {\tau} versus baseline, gains first place in six of eight Production Complexity metrics, and ranks among the top three on 17 of 32 challenge metrics.

In crowded settings, the human brain can focus on speech from a target speaker, given prior knowledge of how they sound. We introduce a novel intelligent hearable system that achieves this capability, enabling target speech hearing to ignore all interfering speech and noise, but the target speaker. A naive approach is to require a clean speech example to enroll the target speaker. This is however not well aligned with the hearable application domain since obtaining a clean example is challenging in real world scenarios, creating a unique user interface problem. We present the first enrollment interface where the wearer looks at the target speaker for a few seconds to capture a single, short, highly noisy, binaural example of the target speaker. This noisy example is used for enrollment and subsequent speech extraction in the presence of interfering speakers and noise. Our system achieves a signal quality improvement of 7.01 dB using less than 5 seconds of noisy enrollment audio and can process 8 ms of audio chunks in 6.24 ms on an embedded CPU. Our user studies demonstrate generalization to real-world static and mobile speakers in previously unseen indoor and outdoor multipath environments. Finally, our enrollment interface for noisy examples does not cause performance degradation compared to clean examples, while being convenient and user-friendly. Taking a step back, this paper takes an important step towards enhancing the human auditory perception with artificial intelligence. We provide code and data at: https://github.com/vb000/LookOnceToHear.

The thud of a bouncing ball, the onset of speech as lips open -- when visual and audio events occur together, it suggests that there might be a common, underlying event that produced both signals. In this paper, we argue that the visual and audio components of a video signal should be modeled jointly using a fused multisensory representation. We propose to learn such a representation in a self-supervised way, by training a neural network to predict whether video frames and audio are temporally aligned. We use this learned representation for three applications: (a) sound source localization, i.e. visualizing the source of sound in a video; (b) audio-visual action recognition; and (c) on/off-screen audio source separation, e.g. removing the off-screen translator's voice from a foreign official's speech. Code, models, and video results are available on our webpage: http://andrewowens.com/multisensory

Laughter is one of the most expressive and natural aspects of human speech, conveying emotions, social cues, and humor. However, most text-to-speech (TTS) systems lack the ability to produce realistic and appropriate laughter sounds, limiting their applications and user experience. While there have been prior works to generate natural laughter, they fell short in terms of controlling the timing and variety of the laughter to be generated. In this work, we propose ELaTE, a zero-shot TTS that can generate natural laughing speech of any speaker based on a short audio prompt with precise control of laughter timing and expression. Specifically, ELaTE works on the audio prompt to mimic the voice characteristic, the text prompt to indicate the contents of the generated speech, and the input to control the laughter expression, which can be either the start and end times of laughter, or the additional audio prompt that contains laughter to be mimicked. We develop our model based on the foundation of conditional flow-matching-based zero-shot TTS, and fine-tune it with frame-level representation from a laughter detector as additional conditioning. With a simple scheme to mix small-scale laughter-conditioned data with large-scale pre-training data, we demonstrate that a pre-trained zero-shot TTS model can be readily fine-tuned to generate natural laughter with precise controllability, without losing any quality of the pre-trained zero-shot TTS model. Through the evaluations, we show that ELaTE can generate laughing speech with significantly higher quality and controllability compared to conventional models. See https://aka.ms/elate/ for demo samples.

Recent studies have addressed intricate phonological phenomena in French, relying on either extensive linguistic knowledge or a significant amount of sentence-level pronunciation data. However, creating such resources is expensive and non-trivial. To this end, we propose a novel two-step approach that encompasses two pronunciation tasks: grapheme-to-phoneme and post-lexical processing. We then investigate the efficacy of the proposed approach with a notably limited amount of sentence-level pronunciation data. Our findings demonstrate that the proposed two-step approach effectively mitigates the lack of extensive labeled data, and serves as a feasible solution for addressing French phonological phenomena even under resource-constrained environments.

Prosody plays an important role in characterizing the style of a speaker or an emotion, but most non-parallel voice or emotion style transfer algorithms do not convert any prosody information. Two major components of prosody are pitch and rhythm. Disentangling the prosody information, particularly the rhythm component, from the speech is challenging because it involves breaking the synchrony between the input speech and the disentangled speech representation. As a result, most existing prosody style transfer algorithms would need to rely on some form of text transcriptions to identify the content information, which confines their application to high-resource languages only. Recently, SpeechSplit has made sizeable progress towards unsupervised prosody style transfer, but it is unable to extract high-level global prosody style in an unsupervised manner. In this paper, we propose AutoPST, which can disentangle global prosody style from speech without relying on any text transcriptions. AutoPST is an Autoencoder-based Prosody Style Transfer framework with a thorough rhythm removal module guided by the self-expressive representation learning. Experiments on different style transfer tasks show that AutoPST can effectively convert prosody that correctly reflects the styles of the target domains.

Word embeddings that map words into a fixed-dimensional vector space are the backbone of modern NLP. Most word embedding methods encode semantic information. However, phonetic information, which is important for some tasks, is often overlooked. In this work, we develop several novel methods which leverage articulatory features to build phonetically informed word embeddings, and present a set of phonetic word embeddings to encourage their community development, evaluation and use. While several methods for learning phonetic word embeddings already exist, there is a lack of consistency in evaluating their effectiveness. Thus, we also proposes several ways to evaluate both intrinsic aspects of phonetic word embeddings, such as word retrieval and correlation with sound similarity, and extrinsic performances, such as rhyme and cognate detection and sound analogies. We hope that our suite of tasks will promote reproducibility and provide direction for future research on phonetic word embeddings.

Recognizing whispered speech and converting it to normal speech creates many possibilities for speech interaction. Because the sound pressure of whispered speech is significantly lower than that of normal speech, it can be used as a semi-silent speech interaction in public places without being audible to others. Converting whispers to normal speech also improves the speech quality for people with speech or hearing impairments. However, conventional speech conversion techniques do not provide sufficient conversion quality or require speaker-dependent datasets consisting of pairs of whispered and normal speech utterances. To address these problems, we propose WESPER, a zero-shot, real-time whisper-to-normal speech conversion mechanism based on self-supervised learning. WESPER consists of a speech-to-unit (STU) encoder, which generates hidden speech units common to both whispered and normal speech, and a unit-to-speech (UTS) decoder, which reconstructs speech from the encoded speech units. Unlike the existing methods, this conversion is user-independent and does not require a paired dataset for whispered and normal speech. The UTS decoder can reconstruct speech in any target speaker's voice from speech units, and it requires only an unlabeled target speaker's speech data. We confirmed that the quality of the speech converted from a whisper was improved while preserving its natural prosody. Additionally, we confirmed the effectiveness of the proposed approach to perform speech reconstruction for people with speech or hearing disabilities. (project page: http://lab.rekimoto.org/projects/wesper )

At present, Text-to-speech (TTS) systems that are trained with high-quality transcribed speech data using end-to-end neural models can generate speech that is intelligible, natural, and closely resembles human speech. These models are trained with relatively large single-speaker professionally recorded audio, typically extracted from audiobooks. Meanwhile, due to the scarcity of freely available speech corpora of this kind, a larger gap exists in Arabic TTS research and development. Most of the existing freely available Arabic speech corpora are not suitable for TTS training as they contain multi-speaker casual speech with variations in recording conditions and quality, whereas the corpus curated for speech synthesis are generally small in size and not suitable for training state-of-the-art end-to-end models. In a move towards filling this gap in resources, we present a speech corpus for Classical Arabic Text-to-Speech (ClArTTS) to support the development of end-to-end TTS systems for Arabic. The speech is extracted from a LibriVox audiobook, which is then processed, segmented, and manually transcribed and annotated. The final ClArTTS corpus contains about 12 hours of speech from a single male speaker sampled at 40100 kHz. In this paper, we describe the process of corpus creation and provide details of corpus statistics and a comparison with existing resources. Furthermore, we develop two TTS systems based on Grad-TTS and Glow-TTS and illustrate the performance of the resulting systems via subjective and objective evaluations. The corpus will be made publicly available at www.clartts.com for research purposes, along with the baseline TTS systems demo.

Neural text-to-speech (TTS) has achieved human-like synthetic speech for single-speaker, single-language synthesis. Multilingual TTS systems are limited to resource-rich languages due to the lack of large paired text and studio-quality audio data. In most cases, TTS systems are built using a single speaker's voice. However, there is growing interest in developing systems that can synthesize voices for new speakers using only a few seconds of their speech. This paper presents ZMM-TTS, a multilingual and multispeaker framework utilizing quantized latent speech representations from a large-scale, pre-trained, self-supervised model. Our paper is the first to incorporate the representations from text-based and speech-based self-supervised learning models into multilingual speech synthesis tasks. We conducted comprehensive subjective and objective evaluations through a series of experiments. Our model has been proven effective in terms of speech naturalness and similarity for both seen and unseen speakers in six high-resource languages. We also tested the efficiency of our method on two hypothetical low-resource languages. The results are promising, indicating that our proposed approach can synthesize audio that is intelligible and has a high degree of similarity to the target speaker's voice, even without any training data for the new, unseen language.

Token-based text-to-speech (TTS) models have emerged as a promising avenue for generating natural and realistic speech, yet they grapple with low pronunciation accuracy, speaking style and timbre inconsistency, and a substantial need for diverse training data. In response, we introduce a novel hierarchical acoustic modeling approach complemented by a tailored data augmentation strategy and train it on the combination of real and synthetic data, scaling the data size up to 650k hours, leading to the zero-shot TTS model with 0.8B parameters. Specifically, our method incorporates a latent variable sequence containing supplementary acoustic information based on refined self-supervised learning (SSL) discrete units into the TTS model by a predictor. This significantly mitigates pronunciation errors and style mutations in synthesized speech. During training, we strategically replace and duplicate segments of the data to enhance timbre uniformity. Moreover, a pretrained few-shot voice conversion model is utilized to generate a plethora of voices with identical content yet varied timbres. This facilitates the explicit learning of utterance-level one-to-many mappings, enriching speech diversity and also ensuring consistency in timbre. Comparative experiments (Demo page: https://anonymous.4open.science/w/ham-tts/)demonstrate our model's superiority over VALL-E in pronunciation precision and maintaining speaking style, as well as timbre continuity.

We present a state-of-the-art speech recognition system developed using end-to-end deep learning. Our architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these traditional systems also tend to perform poorly when used in noisy environments. In contrast, our system does not need hand-designed components to model background noise, reverberation, or speaker variation, but instead directly learns a function that is robust to such effects. We do not need a phoneme dictionary, nor even the concept of a "phoneme." Key to our approach is a well-optimized RNN training system that uses multiple GPUs, as well as a set of novel data synthesis techniques that allow us to efficiently obtain a large amount of varied data for training. Our system, called Deep Speech, outperforms previously published results on the widely studied Switchboard Hub5'00, achieving 16.0% error on the full test set. Deep Speech also handles challenging noisy environments better than widely used, state-of-the-art commercial speech systems.

We introduce Noise2Music, where a series of diffusion models is trained to generate high-quality 30-second music clips from text prompts. Two types of diffusion models, a generator model, which generates an intermediate representation conditioned on text, and a cascader model, which generates high-fidelity audio conditioned on the intermediate representation and possibly the text, are trained and utilized in succession to generate high-fidelity music. We explore two options for the intermediate representation, one using a spectrogram and the other using audio with lower fidelity. We find that the generated audio is not only able to faithfully reflect key elements of the text prompt such as genre, tempo, instruments, mood, and era, but goes beyond to ground fine-grained semantics of the prompt. Pretrained large language models play a key role in this story -- they are used to generate paired text for the audio of the training set and to extract embeddings of the text prompts ingested by the diffusion models. Generated examples: https://google-research.github.io/noise2music

We introduce Moshi, a speech-text foundation model and full-duplex spoken dialogue framework. Current systems for spoken dialogue rely on pipelines of independent components, namely voice activity detection, speech recognition, textual dialogue and text-to-speech. Such frameworks cannot emulate the experience of real conversations. First, their complexity induces a latency of several seconds between interactions. Second, text being the intermediate modality for dialogue, non-linguistic information that modifies meaning -- such as emotion or non-speech sounds -- is lost in the interaction. Finally, they rely on a segmentation into speaker turns, which does not take into account overlapping speech, interruptions and interjections. Moshi solves these independent issues altogether by casting spoken dialogue as speech-to-speech generation. Starting from a text language model backbone, Moshi generates speech as tokens from the residual quantizer of a neural audio codec, while modeling separately its own speech and that of the user into parallel streams. This allows for the removal of explicit speaker turns, and the modeling of arbitrary conversational dynamics. We moreover extend the hierarchical semantic-to-acoustic token generation of previous work to first predict time-aligned text tokens as a prefix to audio tokens. Not only this "Inner Monologue" method significantly improves the linguistic quality of generated speech, but we also illustrate how it can provide streaming speech recognition and text-to-speech. Our resulting model is the first real-time full-duplex spoken large language model, with a theoretical latency of 160ms, 200ms in practice, and is available at https://github.com/kyutai-labs/moshi.

Recent advances in audio generation have focused on text-to-audio (T2A) and video-to-audio (V2A) tasks. However, T2A or V2A methods cannot generate holistic sounds (onscreen and off-screen). This is because T2A cannot generate sounds aligning with onscreen objects, while V2A cannot generate semantically complete (offscreen sounds missing). In this work, we address the task of holistic audio generation: given a video and a text prompt, we aim to generate both onscreen and offscreen sounds that are temporally synchronized with the video and semantically aligned with text and video. Previous approaches for joint text and video-to-audio generation often suffer from modality bias, favoring one modality over the other. To overcome this limitation, we introduce VinTAGe, a flow-based transformer model that jointly considers text and video to guide audio generation. Our framework comprises two key components: a Visual-Text Encoder and a Joint VT-SiT model. To reduce modality bias and improve generation quality, we employ pretrained uni-modal text-to-audio and video-to-audio generation models for additional guidance. Due to the lack of appropriate benchmarks, we also introduce VinTAGe-Bench, a dataset of 636 video-text-audio pairs containing both onscreen and offscreen sounds. Our comprehensive experiments on VinTAGe-Bench demonstrate that joint text and visual interaction is necessary for holistic audio generation. Furthermore, VinTAGe achieves state-of-the-art results on the VGGSound benchmark. Our source code and pre-trained models will be released. Demo is available at: https://www.youtube.com/watch?v=QmqWhUjPkJI.

Recent Text-to-Speech (TTS) systems trained on reading or acted corpora have achieved near human-level naturalness. The diversity of human speech, however, often goes beyond the coverage of these corpora. We believe the ability to handle such diversity is crucial for AI systems to achieve human-level communication. Our work explores the use of more abundant real-world data for building speech synthesizers. We train TTS systems using real-world speech from YouTube and podcasts. We observe the mismatch between training and inference alignments in mel-spectrogram based autoregressive models, leading to unintelligible synthesis, and demonstrate that learned discrete codes within multiple code groups effectively resolves this issue. We introduce our MQTTS system whose architecture is designed for multiple code generation and monotonic alignment, along with the use of a clean silence prompt to improve synthesis quality. We conduct ablation analyses to identify the efficacy of our methods. We show that MQTTS outperforms existing TTS systems in several objective and subjective measures.