FAIR-Play
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Binaural Audio Generation | FAIR-Play | STFT Score1.155 | 11 | |
| Visually Guided Mono-to-Binaural Audio Generation | FAIR-Play (10-split) | STFT Error0.82 | 5 | |
| Audio-Visual Speech Extraction | FAIR-Play | SI-SDR (dB)11.8 | 1 |
Showing 3 of 3 rows