Visual Speech Recognition

Benchmarks

Dataset Name	SOTA Method	Metric
LRS3 (test)	Llama-AVSR	WER0.77	159	4d ago
LRS3 High-Resource, 433h labelled v1 (test)		WER0.009	80	4d ago
LRS3	Auto-AVSR	WER0.009	59	4d ago
LRS2	AutoAVSR	Mean WER14.6	45	4d ago
LRS3 Low-Resource 30h labelled v1 (test)	USR	WER0.024	34	4d ago
LRS3 low-resource (test)		WER19.3	20	4d ago
LRS3 high-resource (test)	RAVEn w/ self-training	WER23.1	16	4d ago
WildVSR	Auto-AVSR	WER38.6	15	4d ago
LRS2 v0.4 (test)	Ours (raw A + V)	WER3.7	14	4d ago
LSVSR (test)	Audio-Ph	Word Error Rate18.3	10	4d ago
LRS3 v0.4 (test)	Ours (raw A + V)	WER2.3	9	4d ago
CMLR	VSR model with prediction-based auxiliary tasks	Best CER8	7	4d ago
CNVSRC-Multi Mandarin (dev)	VALLR-Pin	CER24.1	6	4d ago
LRW	SyncVSR	Top-1 Accuracy80.3	5	4d ago
LRS3 v0.0 (test)	Ours (raw A + V)	WER1.2	5	4d ago
Self-Collected Dataset Mandarin (test)	VALLR-Pin	CER32.22	4	4d ago
CMU-MOSEAS-Spanish (CMes)	CM-seq2seq	Best Score58.1	4	4d ago
CMU-MOSEAS-Portuguese (CMpt) (test)	VSR model with prediction-based auxiliary tasks	Mean WER51.6	4	4d ago
Multilingual TEDx-Spanish (MTes) (test)	VSR model with prediction-based auxiliary tasks	Mean WER56.6	4	4d ago
CMU-MOSEAS French	VSR model with prediction-based auxiliary tasks	Mean WER59.1	4	4d ago
Multilingual TEDx-Portuguese (MTpt) (test)	CM-seq2seq	Mean Accuracy70.2	4	4d ago
Multilingual TEDx Italian (MTit) (test)	VSR model with prediction-based auxiliary tasks	Mean WER57.9	4	4d ago
LRS3-TED Full (test)	V2P	WER55.1	2	4d ago
LRS3-TED Filtered (test)	V2P	WER47	1	4d ago

Showing 24 of 24 rows