Configurable EBEN (M=4, P=1, Q=4)

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

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

Audio4 results

Speech EnhancementonVibraVox (temple vibration pickup)
EER (ECAPA2)· 2024-07-16
0.1622
SOTA
Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors arXiv:2407.11828
Speech EnhancementonVibraVox (temple vibration pickup)
Noresqua-MOS· 2024-07-16
3.632
SOTA
Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors arXiv:2407.11828
Speech EnhancementonVibraVox (temple vibration pickup)
PER (wav2vec2)· 2024-07-16
0.391
SOTA
Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors arXiv:2407.11828
Speech EnhancementonVibraVox (temple vibration pickup)
STOI· 2024-07-16
0.763
SOTA
Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors arXiv:2407.11828