Audio-Visual Speech Recognition (AVSR) leverages audio and visual modalities to improve robustness in noisy environments. Recent advances in Large Language Models (LLMs) show strong performance in speech recognition, including AVSR. However, the long speech representations lead to high computational costs for LLMs. Prior methods compress inputs before feeding them to LLMs, but high compression often harms accuracy. To address this, we propose Llama-MTSK, the first Matryoshka-based Multimodal LLM for AVSR, which flexibly adapts audio-visual token allocation under varying compute constraints. Inspired by Matryoshka Representation Learning, our model encodes representations at multiple granularities with a single architecture, avoiding the need for separate models. For efficient fine-tuning, we introduce three LoRA-based strategies using global and scale-specific modules. Evaluations on major AVSR datasets show Llama-MTSK matches or outperforms models trained at fixed compression levels.
AISHELL6-whisper: A Chinese Mandarin Audio-visual Whisper Speech Dataset with Speech Recognition Baselines
School of Computer Science, Wuhan University（武汉大学计算机学院）；School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院）；Beijing AISHELL Technology Co., Ltd.（北京AISHELL科技有限公司）；AI Center, OPPO（OPPO人工智能中心）
Imperial College London（帝国理工学院）；Samsung AI Centre, Cambridge（三星人工智能中心（剑桥））；Facebook London（Facebook（伦敦））
The intuitive interaction between the audio and visual modalities is valuable for cross-modal self-supervised learning. This concept has been demonstrated for generic audiovisual tasks like video action recognition and acoustic scene classification. However, self-supervision remains under-explored for audiovisual speech. We propose a method to learn self-supervised speech representations from the raw audio waveform. We train a raw audio encoder by combining audio-only self-supervision (by predicting informative audio attributes) with visual self-supervision (by generating talking faces from au…
This paper focuses on designing a noise-robust end-to-end Audio-Visual Speech Recognition (AVSR) system. To this end, we propose Visual Context-driven Audio Feature Enhancement module (V-CAFE) to enhance the input noisy audio speech with a help of audio-visual correspondence. The proposed V-CAFE is designed to capture the transition of lip movements, namely visual context and to generate a noise reduction mask by considering the obtained visual context. Through context-dependent modeling, the ambiguity in viseme-to-phoneme mapping can be refined for mask generation. The noisy representations a…
Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）；Meta AI
Video recordings of speech contain correlated audio and visual information, providing a strong signal for speech representation learning from the speaker's lip movements and the produced sound. We introduce Audio-Visual Hidden Unit BERT (AV-HuBERT), a self-supervised representation learning framework for audio-visual speech, which masks multi-stream video input and predicts automatically discovered and iteratively refined multimodal hidden units. AV-HuBERT learns powerful audio-visual speech representation benefiting both lip-reading and automatic speech recognition. On the largest public lip-…
Trinity College Dublin（都柏林圣三一学院）；vivo AI Lab（vivo人工智能实验室）；Hubei University of Chinese Medicine（湖北中医药大学）
Audio-visual speech enhancement system is regarded as one of promising solutions for isolating and enhancing speech of desired speaker. Typical methods focus on predicting clean speech spectrum via a naive convolution neural network based encoder-decoder architecture, and these methods a) are not adequate to use data fully, b) are unable to effectively balance audio-visual features. The proposed model alleviates these drawbacks by a) applying a model that fuses audio and visual features layer by layer in encoding phase, and that feeds fused audio-visual features to each corresponding decoder l…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Speech separation aims to separate individual voice from an audio mixture of multiple simultaneous talkers. Although audio-only approaches achieve satisfactory performance, they build on a strategy to handle the predefined conditions, limiting their application in the complex auditory scene. Towards the cocktail party problem, we propose a novel audio-visual speech separation model. In our model, we use the face detector to detect the number of speakers in the scene and use visual information to avoid the permutation problem. To improve our model's generalization ability to unknown speakers, w…
Google Research（谷歌研究院）；The Hebrew University of Jerusalem（耶路撒冷希伯来大学）
We present a joint audio-visual model for isolating a single speech signal from a mixture of sounds such as other speakers and background noise. Solving this task using only audio as input is extremely challenging and does not provide an association of the separated speech signals with speakers in the video. In this paper, we present a deep network-based model that incorporates both visual and auditory signals to solve this task. The visual features are used to "focus" the audio on desired speakers in a scene and to improve the speech separation quality. To train our joint audio-visual model, …
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Audio-visual target speech extraction, which aims to extract a certain speaker's speech from the noisy mixture by looking at lip movements, has made significant progress combining time-domain speech separation models and visual feature extractors (CNN). One problem of fusing audio and video information is that they have different time resolutions. Most current research upsamples the visual features along the time dimension so that audio and video features are able to align in time. However, we believe that lip movement should mostly contain long-term, or phone-level information. Based on this …
The Hong Kong University of Science and Technology（香港科技大学）
Most lip-to-speech (LTS) synthesis models are trained and evaluated under the assumption that the audio-video pairs in the dataset are perfectly synchronized. In this work, we show that the commonly used audio-visual datasets, such as GRID, TCD-TIMIT, and Lip2Wav, can have data asynchrony issues. Training lip-to-speech with such datasets may further cause the model asynchrony issue -- that is, the generated speech and the input video are out of sync. To address these asynchrony issues, we propose a synchronized lip-to-speech (SLTS) model with an automatic synchronization mechanism (ASM) to cor…
Human speech processing is inherently multimodal, where visual cues (lip movements) help to better understand the speech in noise. Lip-reading driven speech enhancement significantly outperforms benchmark audio-only approaches at low signal-to-noise ratios (SNRs). However, at high SNRs or low levels of background noise, visual cues become fairly less effective for speech enhancement. Therefore, a more optimal, context-aware audio-visual (AV) system is required, that contextually utilises both visual and noisy audio features and effectively accounts for different noisy conditions. In this paper…
Université de Lorraine（洛林大学）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；LORIA（洛林计算机科学及其应用研究所）
Deep latent variable generative models based on variational autoencoder (VAE) have shown promising performance for audiovisual speech enhancement (AVSE). The underlying idea is to learn a VAEbased audiovisual prior distribution for clean speech data, and then combine it with a statistical noise model to recover a speech signal from a noisy audio recording and video (lip images) of the target speaker. Existing generative models developed for AVSE do not take into account the sequential nature of speech data, which prevents them from fully incorporating the power of visual data. In this paper, w…
In this paper, we address the problem of separating individual speech signals from videos using audio-visual neural processing. Most conventional approaches utilize frame-wise matching criteria to extract shared information between co-occurring audio and video. Thus, their performance heavily depends on the accuracy of audio-visual synchronization and the effectiveness of their representations. To overcome the frame discontinuity problem between two modalities due to transmission delay mismatch or jitter, we propose a cross-modal affinity network (CaffNet) that learns global correspondence as …
Academia Sinica（中央研究院）；National Taiwan University（台湾大学）；Mackay Medical College（马偕医学院）
Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent success of convolutional neural networks (CNNs) in SE, we propose an audio-visual deep CNNs (AVDCNN) SE model, which incorporates audio and visual streams into a unified network model. We also propose a multi-task learning framework for reconstructing audio and visual signals at the output layer. Precisely speaking, the proposed AVDCNN model is structured as an …
Purification Before Fusion: Toward Mask-Free Speech Enhancement for Robust Audio-Visual Speech Recognition
University of Electronic Science and Technology of China（电子科技大学）；Defense Innovation Institute, Academy of Military Sciences（国防科技创新研究院）；Peking University（北京大学）；High-tech Institute（高新技术研究所）
University of Science and Technology of China（中国科学技术大学）；iFlytek Research, iFlytek Co., Ltd.（科大讯飞股份有限公司讯飞研究院）；Institute of Acoustics, Chinese Academy of Sciences（中国科学院声学研究所）
With the advance in self-supervised learning for audio and visual modalities, it has become possible to learn a robust audio-visual speech representation. This would be beneficial for improving the audio-visual speech recognition (AVSR) performance, as the multi-modal inputs contain more fruitful information in principle. In this paper, based on existing self-supervised representation learning methods for audio modality, we therefore propose an audio-visual representation learning approach. The proposed approach explores both the complementarity of audio-visual modalities and long-term context…
Audio-visual speech recognition (AVSR) system is thought to be one of the most promising solutions for robust speech recognition, especially in noisy environment. In this paper, we propose a novel multimodal attention based method for audio-visual speech recognition which could automatically learn the fused representation from both modalities based on their importance. Our method is realized using state-of-the-art sequence-to-sequence (Seq2seq) architectures. Experimental results show that relative improvements from 2% up to 36% over the auditory modality alone are obtained depending on the di…
Multi-modal based speech separation has exhibited a specific advantage on isolating the target character in multi-talker noisy environments. Unfortunately, most of current separation strategies prefer a straightforward fusion based on feature learning of each single modality, which is far from sufficient consideration of inter-relationships between modalites. Inspired by learning joint feature representations from audio and visual streams with attention mechanism, in this study, a novel cross-modal fusion strategy is proposed to benefit the whole framework with semantic correlations between di…
Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent success of convolutional neural networks (CNNs) in SE, we propose an audio-visual deep CNNs (AVDCNN) SE model, which incorporates audio and visual streams into a unified network model. We also propose a multi-task learning framework for reconstructing audio and visual signals at the output layer. Precisely speaking, the proposed AVDCNN model is structured as an …
Despite the rapid advance of automatic speech recognition (ASR) technologies, accurate recognition of cocktail party speech characterised by the interference from overlapping speakers, background noise and room reverberation remains a highly challenging task to date. Motivated by the invariance of visual modality to acoustic signal corruption, audio-visual speech enhancement techniques have been developed, although predominantly targeting overlapping speech separation and recognition tasks. In this paper, an audio-visual multi-channel speech separation, dereverberation and recognition approach…
Imperial College London（帝国理工学院）；Meta Reality Labs Research（Meta现实实验室）；Meta
Audio-visual speech enhancement aims to extract clean speech from a noisy environment by leveraging not only the audio itself but also the target speaker's lip movements. This approach has been shown to yield improvements over audio-only speech enhancement, particularly for the removal of interfering speech. Despite recent advances in speech synthesis, most audio-visual approaches continue to use spectral mapping/masking to reproduce the clean audio, often resulting in visual backbones added to existing speech enhancement architectures. In this work, we propose LA-VocE, a new two-stage approac…
Adversarial attacks pose a threat to deep learning models. However, research on adversarial detection methods, especially in the multi-modal domain, is very limited. In this work, we propose an efficient and straightforward detection method based on the temporal correlation between audio and video streams. The main idea is that the correlation between audio and video in adversarial examples will be lower than benign examples due to added adversarial noise. We use the synchronisation confidence score as a proxy for audiovisual correlation and based on it we can detect adversarial attacks. To th…
Self supervised representation learning has recently attracted a lot of research interest for both the audio and visual modalities. However, most works typically focus on a particular modality or feature alone and there has been very limited work that studies the interaction between the two modalities for learning self supervised representations. We propose a framework for learning audio representations guided by the visual modality in the context of audiovisual speech. We employ a generative audio-to-video training scheme in which we animate a still image corresponding to a given audio clip a…
Since facial actions such as lip movements contain significant information about speech content, it is not surprising that audio-visual speech enhancement methods are more accurate than their audio-only counterparts. Yet, state-of-the-art approaches still struggle to generate clean, realistic speech without noise artifacts and unnatural distortions in challenging acoustic environments. In this paper, we propose a novel audio-visual speech enhancement framework for high-fidelity telecommunications in AR/VR. Our approach leverages audio-visual speech cues to generate the codes of a neural speech…
Audio-based automatic speech recognition (ASR) degrades significantly in noisy environments and is particularly vulnerable to interfering speech, as the model cannot determine which speaker to transcribe. Audio-visual speech recognition (AVSR) systems improve robustness by complementing the audio stream with the visual information that is invariant to noise and helps the model focus on the desired speaker. However, previous AVSR work focused solely on the supervised learning setup; hence the progress was hindered by the amount of labeled data available. In this work, we present a self-supervis…
We present an introspection of an audiovisual speech enhancement model. In particular, we focus on interpreting how a neural audiovisual speech enhancement model uses visual cues to improve the quality of the target speech signal. We show that visual cues provide not only high-level information about speech activity, i.e., speech/silence, but also fine-grained visual information about the place of articulation. One byproduct of this finding is that the learned visual embeddings can be used as features for other visual speech applications. We demonstrate the effectiveness of the learned visual …
Speech recognition in cocktail-party environments remains a significant challenge for state-of-the-art speech recognition systems, as it is extremely difficult to extract an acoustic signal of an individual speaker from a background of overlapping speech with similar frequency and temporal characteristics. We propose the use of speaker-targeted acoustic and audio-visual models for this task. We complement the acoustic features in a hybrid DNN-HMM model with information of the target speaker's identity as well as visual features from the mouth region of the target speaker. Experimentation was p…
We propose an end to end deep learning approach for generating real-time facial animation from just audio. Specifically, our deep architecture employs deep bidirectional long short-term memory network and attention mechanism to discover the latent representations of time-varying contextual information within the speech and recognize the significance of different information contributed to certain face status. Therefore, our model is able to drive different levels of facial movements at inference and automatically keep up with the corresponding pitch and latent speaking style in the input audio…
Imperial College London（帝国理工学院）；Samsung AI Center, Cambridge（三星人工智能中心（剑桥））
Several audio-visual speech recognition models have been recently proposed which aim to improve the robustness over audio-only models in the presence of noise. However, almost all of them ignore the impact of the Lombard effect, i.e., the change in speaking style in noisy environments which aims to make speech more intelligible and affects both the acoustic characteristics of speech and the lip movements. In this paper, we investigate the impact of the Lombard effect in audio-visual speech recognition. To the best of our knowledge, this is the first work which does so using end-to-end deep arc…
The task of talking head generation is to synthesize a lip synchronized talking head video by inputting an arbitrary face image and audio clips. Most existing methods ignore the local driving information of the mouth muscles. In this paper, we propose a novel recurrent generative network that uses both audio and speech-related facial action units (AUs) as the driving information. AU information related to the mouth can guide the movement of the mouth more accurately. Since speech is highly correlated with speech-related AUs, we propose an Audio-to-AU module in our system to predict the speech-…
