Demucs (bf)

Reported on 2 benchmarks across 2 tasks · 1 paper

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

Audio2 results

Speech RecognitiononEasyCom
WER (%)· 2022-12-21
69.8
best: 52.1 (ReVISE (bf))
ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement arXiv:2212.11377
Speech EnhancementonEasyCom
Audio Quality MOS· 2022-12-21
2.39
best: 4.19 (ReVISE (ch2))
ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement arXiv:2212.11377