| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Target-speaker Automatic Speech Recognition | NOTSOFAR Small-SDM 1 | tcpWER15.8 | 14 | |
| Speaker Diarization | NOTSOFAR-1 | DER8.2 | 9 | |
| Multi-speaker Automatic Speech Recognition | NotSoFar | CP-WER34.48 | 7 | |
| Turn-taking decision | NOTSOFAR NSF-1 (test) | Precision81 | 4 |