Lipreading On Lrs2

评估指标

Word Error Rate (WER)

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
LIBS	65.29	Hearing Lips: Improving Lip Reading by Distilling Speech Recognizers
TM-CTC + extLM	54.7	Deep Audio-Visual Speech Recognition
CTC + KD ASR	53.2	ASR is all you need: cross-modal distillation for lip reading	-
Conv-seq2seq	51.7	Spatio-Temporal Fusion Based Convolutional Sequence Learning for Lip Reading	-
Hybrid CTC / Attention	50	Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture	-
LF-MMI TDNN	48.86	Audio-visual Recognition of Overlapped speech for the LRS2 dataset	-
TM-seq2seq + extLM	48.3	Deep Audio-Visual Speech Recognition
Multi-head Visual-Audio Memory	44.5	Distinguishing Homophenes Using Multi-Head Visual-Audio Memory for Lip Reading
MoCo + wav2vec (w/o extLM)	43.2	Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition
Hybrid CTC / Attention	39.1	End-to-end Audio-visual Speech Recognition with Conformers
CTC/Attention	32.9	Visual Speech Recognition for Multiple Languages in the Wild
ES³ Base*	31.4	ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations	-
ES³ Base	30.7	ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations	-
ES³ Base* + extLM	29.3	ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations	-
SyncVSR	28.9	SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization
VTP	28.9	Sub-word Level Lip Reading With Visual Attention	-
ES³ Base + extLM	28.7	ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations	-
ES³ Large	26.7	ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations	-
CTC/Attention (LRW+LRS2/3+AVSpeech)	25.5	Visual Speech Recognition for Multiple Languages in the Wild
ES³ Large + extLM	24.6	ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations	-

0 of 25 row(s) selected.