Configurable EBEN (M=4, P=4, 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 (forehead accelerometer)
EER (ECAPA2)· 2024-07-16
0.0183
SOTA
Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors arXiv:2407.11828
Speech EnhancementonVibraVox (forehead accelerometer)
Noresqua-MOS· 2024-07-16
4.25
SOTA
Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors arXiv:2407.11828
Speech EnhancementonVibraVox (forehead accelerometer)
PER (wav2vec2)· 2024-07-16
0.091
SOTA
Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors arXiv:2407.11828
Speech EnhancementonVibraVox (forehead accelerometer)
STOI· 2024-07-16
0.855
SOTA
Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors arXiv:2407.11828