Audio-Visual concat-ref

Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Speech2 results

Speech SeparationonGRID corpus (mixed-speech)
SDR· 2018-11-06
8.05
best: 9.6
SOTA
Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments arXiv:1811.02480
Speech SeparationonTCD-TIMIT corpus (mixed-speech)
SDR· 2018-11-06
10.55
SOTA
Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments arXiv:1811.02480

Audio2 results

Speech EnhancementonTCD-TIMIT corpus (mixed-speech)
PESQ· 2018-11-06
3.03
SOTA
Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments arXiv:1811.02480
Speech EnhancementonGRID corpus (mixed-speech)
PESQ· 2018-11-06
2.7
SOTA
Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments arXiv:1811.02480