Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-speaker ASR on LibriSpeech2Mix
Loading...
4
WER
Whisper-medium-SS-TTI [47]
3.64
6.07
8.5
10.93
Aug 28, 2025
WER
Updated 20d ago
Evaluation Results
Method
Method
Links
WER
Whisper-medium-SS-TTI [47]
Training Set=LibriSpee...
2025.08
4
SOT-Conformer [46]
Training Set=LibriSpee...
2025.08
4.9
UME ASR init. (0.33, 0.33, 0.34) w/ RWSE (A4)
Training Set=LibriMix,...
2025.08
5.5
t-SOT [21]
Training Set=LibriSpee...
2025.08
5.8
SURT [45]
Training Set=LibriSpee...
2025.08
7.2
UME (0.33, 0.33, 0.34) + ASR init.
Training Set=LibriMix,...
2025.08
9.2
UME ASR init. (0.33, 0.33, 0.34) w/ RWSE (A3)
Training Set=LibriMix,...
2025.08
10.3
UME (0.33, 0.33, 0.34)
Training Set=LibriMix,...
2025.08
11
SOT [10]
Training Set=LibriSpee...
2025.08
11.2
PIT LSTM-AED [10]
Training Set=LibriSpee...
2025.08
11.9
UME (0.1, 0.1, 0.8)
Training Set=LibriMix,...
2025.08
11.9
Multi-speaker AED [9] (reproduced)
Training Set=LibriMix,...
2025.08
12.7
UME (0.1, 0.1, 0.8) w/ weighted sum
Training Set=LibriMix,...
2025.08
12.8
UME (λasr = 1.0)
Training Set=LibriMix,...
2025.08
13
Feedback
Search any
task
Search any
task