Browse State-of-the-Art › Audio-Visual Speech Recognition
Audio-Visual Speech Recognition
42 papers with code · 4 benchmarks · 7 datasets archive 2025-07-28
Audio-visual speech recognition is the task of transcribing a paired audio and visual stream into text.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
4 leaderboard tables shown for this task, 4 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| LRS3-TED (12 rows) | MMS-LLaMA | MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition... | code | — | Compare |
| LRS2 (8 rows) | Whisper-Flamingo | Whisper-Flamingo: Integrating Visual Features into Whisper for... | code | Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 5 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified | Compare |
| LRW (3 rows) | AVCRFormer | Audio-Visual Speech Recognition based on Regulated Transformer and... | code | — | Compare |
| CAS-VSR-S101 (1 row) | ES³ Base* | ES3: Evolving Self-Supervised Learning of Robust Audio-Visual... | — | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
7 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
1 subtask in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 100 · with a code link: 42 · where Syntology ran a sample: 14 (12 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (14 of 100 tagged: 12 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 100 of 100, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
6 Sep 2018 4 repositories listedThe goal of this work is to recognise phrases and sentences being spoken by a talking face, with or without the audio.
-
12 Feb 2021 3 repositories listedIn this work, we present a hybrid CTC/Attention model based on a ResNet-18 and Convolution-augmented transformer (Conformer), that can be trained in an end-to-end manner.
-
25 Mar 2023 2 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 6 harvested samples) · 2 pointer-only (licence)Recently, the performance of automatic, visual, and audio-visual speech recognition (ASR, VSR, and AV-ASR, respectively) has been substantially improved, mainly due to the use of larger models and training sets.
-
12 May 2020 2 repositories listedVision is often used as a complementary modality for audio speech recognition (ASR), especially in the noisy environment where performance of solo audio modality significantly deteriorates.
-
6 May 2025 1 repository listedThey also enable strong performance in Visual Speech Recognition (VSR) with a WER of 20.
-
MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens14 Mar 2025 1 repository listedAudio-Visual Speech Recognition (AVSR) achieves robust speech recognition in noisy environments by combining auditory and visual information.
-
8 Mar 2025 1 repository listedTo capture the wide spectrum of phonetic and linguistic diversity, we also introduce a Multilingual Audio-Visual Romanized Corpus (MARC) consisting of 2, 916 hours of audio-visual speech data across 82 languages, along…
-
9 Feb 2025 1 repository listedWe also introduce a multi-teacher ensemble method to distill the student, which receives audio-visual data as inputs.
-
3 Feb 2025 1 repository listedIn this work, we propose mWhisper-Flamingo for multilingual AVSR which combines the strengths of a pre-trained audio model (Whisper) and video model (AV-HuBERT).
-
23 Jan 2025 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)Specifically, we suggest a unimodal multi-task learning, which distills cross-modal knowledge and aligns the corrupted modalities, by predicting clean audio targets with corrupted videos, and clean video targets with…
-
3 Jan 2025 1 repository listedUnlike traditional Automatic Speech Recognition (ASR), Audio-Visual Speech Recognition (AVSR) takes audio and visual signals simultaneously to infer the transcription.
-
18 Sep 2024 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified (of 12 harvested samples) · 12 pointer-only (licence)For example, in the audio and speech domains, an LLM can be equipped with (automatic) speech recognition (ASR) abilities by just concatenating the audio tokens, computed with an audio encoder, and the text tokens to…
-
1 Aug 2024 1 repository listedIn this work, we present SynesLM, an unified model which can perform three multimodal language understanding tasks: audio-visual automatic speech recognition(AV-ASR) and visual-aided speech/machine translation(VST/VMT).
-
9 Jul 2024 1 repository listedRecent advances in Audio-Visual Speech Recognition (AVSR) have led to unprecedented achievements in the field, improving the robustness of this type of system in adverse, noisy environments.
-
4 Jul 2024 1 repository listed Syntology official (archive's flag): 12 ran · 12 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified (of 13 harvested samples) · 8 pointer-only (licence)Cross-modal attention modules are introduced to enrich video features with audio information so that speech variability can be taken into account when training on the video temporal dynamics.
-
14 Jun 2024 1 repository listed Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 5 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified (of 18 harvested samples) · 18 pointer-only (licence)Since videos are harder to obtain than audio, the video training data of AVSR models is usually limited to a few thousand hours.
-
9 May 2024 1 repository listedThe article introduces a novel audio-visual speech command recognition transformer (AVCRFormer) specifically designed for robust AVSR.
-
7 Mar 2024 1 repository listedIn this paper, we investigate this contrasting phenomenon from the perspective of modality bias and reveal that an excessive modality bias on the audio caused by dropout is the underlying reason.
-
8 Feb 2024 1 repository listed Syntology 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 6 harvested samples) · 1 pointer-only (licence)Recent studies have successfully shown that large language models (LLMs) can be successfully used for generative error correction (GER) on top of the automatic speech recognition (ASR) output.
-
7 Jan 2024 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 9 harvested samples) · 9 pointer-only (licence)Considering that visual information helps to improve speech recognition performance in noisy scenes, in this work we propose a multichannel multi-modal speech self-supervised learning framework AV-wav2vec2, which…
-
29 Sep 2023 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)This is the first time-frequency domain audio-visual speech separation method to outperform all contemporary time-domain counterparts.
-
14 Aug 2023 1 repository listedIn this paper, we propose two novel techniques to improve audio-visual speech recognition (AVSR) under a pre-training and fine-tuning training framework.
-
18 Jun 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples) · 2 pointer-only (licence)In this work, we investigate the noise-invariant visual modality to strengthen robustness of AVSR, which can adapt to any testing noises while without dependence on noisy training data, a. k. a., unsupervised noise…
-
18 Jun 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample) · 1 pointer-only (licence)In this paper, we aim to learn the shared representations across modalities to bridge their gap.
-
10 Jun 2023 1 repository listedWe demonstrate that OpenSR enables modality transfer from one to any in three different settings (zero-, few- and full-shot), and achieves highly competitive zero-shot performance compared to the existing few-shot and…
-
4 Jun 2023 1 repository listedAudio-visual speech recognition (AVSR) gains increasing attention from researchers as an important part of human-computer interaction.
-
18 May 2023 1 repository listedWe investigate the emergent abilities of the recently proposed web-scale speech model Whisper, by adapting it to unseen tasks with prompt engineering.
-
16 May 2023 1 repository listedHowever, most existing AVSR approaches simply fuse the audio and visual features by concatenation, without explicit interactions to capture the deep correlations between them, which results in sub-optimal multimodal…
-
15 Mar 2023 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)Thus, we firstly analyze that the previous AVSR models are not indeed robust to the corruption of multimodal input streams, the audio and the visual inputs, compared to uni-modal models.
-
1 Mar 2023 1 repository listedWe introduce MuAViC, a multilingual audio-visual corpus for robust speech recognition and robust speech-to-text translation providing 1200 hours of audio-visual speech in 9 languages.
-
16 Jan 2023 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
12 Dec 2022 1 repository listed
-
13 Jul 2022 1 repository listed
-
1 Jun 2022 1 repository listed
-
24 Feb 2022 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples)
-
11 Jan 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)
-
5 Jan 2022 1 repository listed Syntology official: no sample here; runs from other or unrecorded repositories · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
14 Dec 2020 1 repository listed
-
19 May 2020 1 repository listed
-
17 Apr 2020 1 repository listed
-
8 Nov 2019 1 repository listed
-
3 Sep 2018 1 repository listed
-
ViCocktail: Automated Multi-Modal Data Collection for Vietnamese Audio-Visual Speech Recognition5 Jun 2025 0 repositories listed
-
Cocktail-Party Audio-Visual Speech Recognition2 Jun 2025 0 repositories listed
-
Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach20 May 2025 0 repositories listed
-
The Multimodal Information Based Speech Processing (MISP) 2025 Challenge: Audio-Visual Diarization and Recognition20 May 2025 0 repositories listed
-
SwinLip: An Efficient Visual Speech Encoder for Lip Reading Using Swin Transformer7 May 2025 0 repositories listed
-
Chinese-LiPS: A Chinese audio-visual speech recognition dataset with Lip-reading and Presentation Slides21 Apr 2025 0 repositories listed
-
Visual-Aware Speech Recognition for Noisy Scenarios9 Apr 2025 0 repositories listed
-
Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs9 Mar 2025 0 repositories listed
-
MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition11 Feb 2025 0 repositories listed
-
Adapter-Based Multi-Agent AVSR Extension for Pre-Trained ASR Models3 Feb 2025 0 repositories listed
-
Uncovering the Visual Contribution in Audio-Visual Speech Recognition22 Dec 2024 0 repositories listed
-
Quantitative Analysis of Audio-Visual Tasks: An Information-Theoretic Perspective29 Sep 2024 0 repositories listed
-
DCIM-AVSR : Efficient Audio-Visual Speech Recognition via Dual Conformer Interaction Module31 Aug 2024 0 repositories listed
-
MSRS: Training Multimodal Speech Recognition Models from Scratch with Sparse Mask Optimization25 Jun 2024 0 repositories listed
-
Learn2Talk: 3D Talking Face Learns from 2D Talking Face19 Apr 2024 0 repositories listed
-
XLAVS-R: Cross-Lingual Audio-Visual Speech Representation Learning for Noise-Robust Speech Perception21 Mar 2024 0 repositories listed
-
Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer14 Mar 2024 0 repositories listed
-
SlideAVSR: A Dataset of Paper Explanation Videos for Audio-Visual Speech Recognition18 Jan 2024 0 repositories listed
-
MLCA-AVSR: Multi-Layer Cross Attention Fusion based Audio-Visual Speech Recognition7 Jan 2024 0 repositories listed
-
1 Jan 2024 0 repositories listed
-
AV-CPL: Continuous Pseudo-Labeling for Audio-Visual Speech Recognition29 Sep 2023 0 repositories listed
-
The Multimodal Information Based Speech Processing (MISP) 2023 Challenge: Audio-Visual Target Speaker Extraction15 Sep 2023 0 repositories listed
-
The NPU-ASLP System for Audio-Visual Speech Recognition in MISP 2022 Challenge11 Mar 2023 0 repositories listed
-
17 Feb 2023 0 repositories listed
-
AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations10 Feb 2023 0 repositories listed
-
A Multi-Purpose Audio-Visual Corpus for Multi-Modal Persian Speech Recognition: the Arman-AV Dataset21 Jan 2023 0 repositories listed
-
ReVISE: Self-Supervised Speech Resynthesis With Visual Input for Universal and Generalized Speech Regeneration1 Jan 2023 0 repositories listed
-
21 Dec 2022 0 repositories listed
-
Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learning10 Dec 2022 0 repositories listed
-
VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning21 Nov 2022 0 repositories listed
-
Streaming Audio-Visual Speech Recognition with Alignment Regularization3 Nov 2022 0 repositories listed
-
Kaggle Competition: Cantonese Audio-Visual Speech Recognition for In-car Commands6 Jul 2022 0 repositories listed
-
RUSAVIC Corpus: Russian Audio-Visual Speech in Cars1 Jun 2022 0 repositories listed
-
Learning Contextually Fused Audio-visual Representations for Audio-visual Speech Recognition15 Feb 2022 0 repositories listed
-
Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition for Single and Multi-Person Video25 Jan 2022 0 repositories listed
-
Recent Progress in the CUHK Dysarthric Speech Recognition System15 Jan 2022 0 repositories listed
-
Leveraging Uni-Modal Self-Supervised Learning for Multimodal Audio-visual Speech Recognition16 Nov 2021 0 repositories listed
-
Audio-Visual Speech Recognition is Worth 32×32×8 Voxels20 Sep 2021 0 repositories listed
-
Large-vocabulary Audio-visual Speech Recognition in Noisy Environments10 Sep 2021 0 repositories listed
-
Spatio-Temporal Attention Mechanism and Knowledge Distillation for Lip Reading7 Aug 2021 0 repositories listed
-
Fusing information streams in end-to-end audio-visual speech recognition19 Apr 2021 0 repositories listed
-
14 Dec 2020 0 repositories listed
-
25 Oct 2020 0 repositories listed
-
6 Jan 2020 0 repositories listed
-
Detecting Adversarial Attacks On Audiovisual Speech Recognition18 Dec 2019 0 repositories listed
-
Investigating the Lombard Effect Influence on End-to-End Audio-Visual Speech Recognition5 Jun 2019 0 repositories listed
-
Modality Attention for End-to-End Audio-visual Speech Recognition13 Nov 2018 0 repositories listed
-
28 Sep 2018 0 repositories listed
-
Towards Lipreading Sentences with Active Appearance Models29 May 2018 0 repositories listed
-
Multimodal Machine Learning: Integrating Language, Vision and Speech1 Jul 2017 0 repositories listed
-
Deep Multimodal Representation Learning from Temporal Data11 Apr 2017 0 repositories listed
-
Auxiliary Multimodal LSTM for Audio-visual Speech Recognition and Lipreading16 Jan 2017 0 repositories listed
-
Audio Visual Speech Recognition using Deep Recurrent Neural Networks9 Nov 2016 0 repositories listed
-
Deep Multimodal Learning for Audio-Visual Speech Recognition22 Jan 2015 0 repositories listed
-
Visual Speech Recognition3 Sep 2014 0 repositories listed
-
Recognition of Isolated Words using Zernike and MFCC features for Audio Visual Speech Recognition4 Jul 2014 0 repositories listed
-
Building a synchronous corpus of acoustic and 3D facial marker data for adaptive audio-visual speech synthesis1 May 2012 0 repositories listed
-
SUTAV: A Turkish Audio-Visual Database1 May 2012 0 repositories listed
Syntology lines on 15 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections