Target-speaker Automatic Speech Recognition
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
15.8tcpWER
14
Jun 17, 2026
14.3tcpWER
5
Feb 26, 2026
11tcpWER
4
Feb 26, 2026
9.7tcpWER
3
Feb 26, 2026
19.9tcpWER
3
Feb 26, 2026
0.028tcpWER
3
Feb 26, 2026
7.7tcpWER (%)
3
Feb 26, 2026
2.9tcpWER
3
Feb 26, 2026
2.1tcpWER (%)
3
Feb 26, 2026
1.7tcpWER
3
Feb 26, 2026