Speaker Diarization on Libri2Mix
1.37DERUME ASR init. (0.33, 0.33, 0.34)
Evaluation Results
| Method | Links | |
|---|---|---|
| UME ASR init. (0.33, 0.33, 0.34)Training set=LibriMix (460 hours), Mixture type=mixclean: speech only, Mode=max, Weighting scheme=w/ RWSE, Training weights (λasr, λdiar, λsep)=(0.33, 0.33, 0.34), ASR initialization=true, Collar tolerance=None2025.08 | 1.37 | |
| UME ASR init. (0.33, 0.33, 0.34)Training set=LibriMix (460 hours), Mixture type=mixboth: speech + noise, Mode=max, Weighting scheme=w/ RWSE, Training weights (λasr, λdiar, λsep)=(0.33, 0.33, 0.34), ASR initialization=true, Collar tolerance=None2025.08 | 2.14 | |
| UME (0.1, 0.1, 0.8)Training set=LibriMix (460 hours), Mixture type=mixboth: speech + noise, Mode=max, Weighting scheme=w/ weighted sum, Training weights (λasr, λdiar, λsep)=(0.1, 0.1, 0.8), ASR initialization=false, Collar tolerance=None2025.08 | 2.19 | |
| UME (0.33, 0.33, 0.34)Training set=LibriMix (460 hours), Mixture type=mixboth: speech + noise, Mode=max, Weighting scheme=w/ weighted sum, Training weights (λasr, λdiar, λsep)=(0.33, 0.33, 0.34), ASR initialization=false, Collar tolerance=None2025.08 | 2.26 | |
| UME (0.1, 0.1, 0.8)Training set=LibriMix (460 hours), Mixture type=mixboth: speech + noise, Mode=max, Weighting scheme=w/o weighted sum, Training weights (λasr, λdiar, λsep)=(0.1, 0.1, 0.8), Collar tolerance=None2025.08 | 2.28 | |
| UME (0.33, 0.33, 0.34) + ASR init.Training set=LibriMix (460 hours), Mixture type=mixboth: speech + noise, Mode=max, Weighting scheme=w/ weighted sum, Training weights (λasr, λdiar, λsep)=(0.33, 0.33, 0.34), ASR initialization=true, Collar tolerance=None2025.08 | 2.45 | |
| UME (λdiar = 1.0)Training set=LibriMix (460 hours), Mixture type=mixboth: speech + noise, Mode=max, Weighting scheme=w/o weighted sum, Training weights (λasr, λdiar, λsep)=(0, 1.0, 0), Collar tolerance=None2025.08 | 2.91 | |
| WavLM Large [32]Training set=LibriMix (100 hours), Mixture type=mixclean: speech only, Mode=max, Collar tolerance=None2025.08 | 3.24 | |
| EEND [2] (reprod.)Training set=LibriMix (460 hours), Mixture type=mixboth: speech + noise, Mode=max, Collar tolerance=None2025.08 | 4.62 | |
| wav2vec 2.0 Large [30]Training set=LibriMix (100 hours), Mixture type=mixclean: speech only, Mode=max, Collar tolerance=None2025.08 | 5.62 | |
| HuBERT Large [31]Training set=LibriMix (100 hours), Mixture type=mixclean: speech only, Mode=max, Collar tolerance=None2025.08 | 5.75 |