| LP + Conformer |
- Word Error Rate (WER)
- 12.8
|
Conformers are All You Need for Visual Speech Recognition
2023-02-17 |
연결 없음 |
| Auto-AVSR |
- Word Error Rate (WER)
- 19.1
|
Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels
2023-03-25 |
코드 1 · 코드 2 |
| SyncVSR |
- Word Error Rate (WER)
- 31.2
|
SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization
2024-06-18 |
코드 1 |
| USR (self + semi-supervised) |
- Word Error Rate (WER)
- 21.5
|
Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs
2024-11-04 |
코드 1 |
| USR (self-supervised) |
- Word Error Rate (WER)
- 22.3
|
Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs
2024-11-04 |
코드 1 |
| RAVEn Large |
- Word Error Rate (WER)
- 23.4
|
Jointly Learning Visual and Auditory Speech Representations from Raw Data
2022-12-12 |
코드 1 |
| VSP-LLM |
- Word Error Rate (WER)
- 25.4
|
Where Visual Speech Meets Language: VSP-LLM Framework for Efficient and Context-Aware Visual Speech Processing
2024-02-23 |
코드 1 |
| AV-HuBERT Large + Relaxed Attention + LM |
- Word Error Rate (WER)
- 25.51
|
Relaxed Attention for Transformer Models
2022-09-20 |
코드 1 |
| DistillAV |
- Word Error Rate (WER)
- 26.2
|
Audio-Visual Representation Learning via Knowledge Distillation from Speech Foundation Models
2025-02-09 |
코드 1 |
| AV-HuBERT Large |
- Word Error Rate (WER)
- 26.9
|
Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction
2022-01-05 |
코드 1 · 코드 2 |
| VTP (more data) |
- Word Error Rate (WER)
- 30.7
|
Sub-word Level Lip Reading With Visual Attention
2021-10-14 |
연결 없음 |
| CTC/Attention (LRW+LRS2/3+AVSpeech) |
- Word Error Rate (WER)
- 31.5
|
Visual Speech Recognition for Multiple Languages in the Wild
2022-02-26 |
코드 1 · 코드 2 |
| RNN-T |
- Word Error Rate (WER)
- 33.6
|
Recurrent Neural Network Transducer for Audio-Visual Speech Recognition
2019-11-08 |
코드 1 |
| ES³ Large |
- Word Error Rate (WER)
- 37.1
|
ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations
2024-01-01 |
연결 없음 |
| ES³ Base |
- Word Error Rate (WER)
- 40.3
|
ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations
2024-01-01 |
연결 없음 |
| VTP |
- Word Error Rate (WER)
- 40.6
|
Sub-word Level Lip Reading With Visual Attention
2021-10-14 |
연결 없음 |
| Hyb + Conformer |
- Word Error Rate (WER)
- 43.3
|
End-to-end Audio-visual Speech Recognition with Conformers
2021-02-12 |
코드 1 · 코드 2 · 코드 3 |
| CTC-V2P |
- Word Error Rate (WER)
- 55.1
|
Large-Scale Visual Speech Recognition
2018-07-13 |
연결 없음 |
| EG-seq2seq |
- Word Error Rate (WER)
- 57.8
|
Discriminative Multi-modality Speech Recognition
2020-05-12 |
코드 1 · 코드 2 |
| TM-seq2seq |
- Word Error Rate (WER)
- 58.9
|
Deep Audio-Visual Speech Recognition
2018-09-06 |
코드 1 · 코드 2 · 코드 3 · 코드 4 |
| CTC + KD |
- Word Error Rate (WER)
- 59.8
|
ASR is all you need: cross-modal distillation for lip reading
2019-11-28 |
연결 없음 |
| Conv-seq2seq |
- Word Error Rate (WER)
- 60.1
|
Spatio-Temporal Fusion Based Convolutional Sequence Learning for Lip Reading
2019-10-01 |
연결 없음 |