List your company

Multi-speaker ASR on Libri2Mix mixclean

6.4WERUME ASR init. (0.33, 0.33, 0.34) w/ RWSE
6.39366.43686.486.5232Aug 28, 2025

Evaluation results

MethodLinks
UME ASR init. (0.33, 0.33, 0.34) w/ RWSETraining Set=LibriMix, Training hours=460 hours, Mix Type=mixclean: speech only, Overlap Mode=max, Initialization=ASR init., Training weights (λasr, λdiar, λsep)=(0.33, 0.33, 0.34), RWSE=true2025.086.4
Whisper-medium-SS-TTI [47]Training Set=LibriMix, Training hours=unk. hours, Mix Type=mixclean: speech only, Overlap Mode=max2025.086.56