SOTAVerified

Audio-Visual Speech Recognition

Audio-visual speech recognition is the task of transcribing a paired audio and visual stream into text.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 76–100 of 100 papers

TitleStatusHype
ReVISE: Self-Supervised Speech Resynthesis With Visual Input for Universal and Generalized Speech Regeneration—0
Audio-Visual Speech Recognition is Worth 32328 Voxels—0
Audio Visual Speech Recognition using Deep Recurrent Neural Networks—0
Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture—0
Auxiliary Multimodal LSTM for Audio-visual Speech Recognition and Lipreading—0
AV-CPL: Continuous Pseudo-Labeling for Audio-Visual Speech Recognition—0
AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations—0
Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs—0
Building a synchronous corpus of acoustic and 3D facial marker data for adaptive audio-visual speech synthesis—0
Chinese-LiPS: A Chinese audio-visual speech recognition dataset with Lip-reading and Presentation Slides—0
RUSAVIC Corpus: Russian Audio-Visual Speech in Cars—0
Cocktail-Party Audio-Visual Speech Recognition—0
Audio-Visual Speech and Gesture Recognition by Sensors of Mobile Devices—0
Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach—0
DCIM-AVSR : Efficient Audio-Visual Speech Recognition via Dual Conformer Interaction Module—0
Visual Speech Recognition—0
Deep Multimodal Learning for Audio-Visual Speech Recognition—0
Deep Multimodal Representation Learning from Temporal Data—0
Listening and Seeing Again: Generative Error Correction for Audio-Visual Speech RecognitionCode0
LRS3-TED: a large-scale dataset for visual speech recognitionCode0
Audio-Visual Speech Recognition based on Regulated Transformer and Spatio-Temporal Fusion Strategy for Driver Assistive SystemsCode0
Recurrent Neural Network Transducer for Audio-Visual Speech RecognitionCode0
A Study of Dropout-Induced Modality Bias on Robustness to Missing Video Frames for Audio-Visual Speech RecognitionCode0
Multichannel AV-wav2vec2: A Framework for Learning Multichannel Multi-Modal Speech RepresentationCode0
SynesLM: A Unified Approach for Audio-visual Speech Recognition and Translation via Language Model and Synthetic DataCode0
Show:102550
← PrevPage 4 of 4Next →
All datasetsLRS2LRS3-TEDLRWCAS-VSR-S101

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Hybrid CTC / AttentionWord Error Rate (WER)39.1—Unverified
2TM-Seq2seqTest WER8.5—Unverified
3TM-CTCTest WER8.2—Unverified
4CTC/AttentionTest WER7—Unverified
5CTC/AttentionTest WER1.5—Unverified
6Whisper-FlamingoTest WER1.4—Unverified
#ModelMetricClaimedVerifiedStatus
1Hyb-ConformerWord Error Rate (WER)2.3—Unverified
2Zero-AVSRWord Error Rate (WER)1.5—Unverified
3AV-HuBERT LargeWord Error Rate (WER)1.4—Unverified
4Whisper-FlamingoWord Error Rate (WER)0.76—Unverified
5MMS-LLaMAWord Error Rate (WER)0.74—Unverified
#ModelMetricClaimedVerifiedStatus
1AVCRFormerTop-1 Accuracy98.81—Unverified
22DCNN + BiLSTM + ResNet + MLFTop-1 Accuracy98.76—Unverified
3PBLTop-1 Accuracy98.3—Unverified
#ModelMetricClaimedVerifiedStatus
1ES³ Base*Word Error Rate (WER)11—Unverified