List your company

Multi-speaker ASR on Libri2Mix mixboth

19.6WERUME ASR init. (0.33, 0.33, 0.34) w/ RWSE
19.36420.95722.5524.143Aug 28, 2025

Evaluation results

MethodLinks
UME ASR init. (0.33, 0.33, 0.34) w/ RWSETraining Set=LibriMix, Training hours=460 hours, Mix Type=mixboth: speech + noise, Overlap Mode=max, Initialization=ASR init., Training weights (λasr, λdiar, λsep)=(0.33, 0.33, 0.34), RWSE=true2025.0819.6
UME (0.33, 0.33, 0.34) + ASR init.Training Set=LibriMix, Training hours=460 hours, Mix Type=mixboth: speech + noise, Overlap Mode=max, Initialization=ASR init., Training weights (λasr, λdiar, λsep)=(0.33, 0.33, 0.34)2025.0821.1
UME (0.1, 0.1, 0.8)Training Set=LibriMix, Training hours=460 hours, Mix Type=mixboth: speech + noise, Overlap Mode=max, Training weights (λasr, λdiar, λsep)=(0.1, 0.1, 0.8)2025.0822.4
UME (0.33, 0.33, 0.34)Training Set=LibriMix, Training hours=460 hours, Mix Type=mixboth: speech + noise, Overlap Mode=max, Training weights (λasr, λdiar, λsep)=(0.33, 0.33, 0.34)2025.0822.7
Multi-speaker AED [9] (reproduced)Training Set=LibriMix, Training hours=460 hours, Mix Type=mixboth: speech + noise, Overlap Mode=max2025.0824.4
UME (λasr = 1.0)Training Set=LibriMix, Training hours=460 hours, Mix Type=mixboth: speech + noise, Overlap Mode=max, Training weights (λasr, λdiar, λsep)=(1.0, 0, 0)2025.0825
UME (0.1, 0.1, 0.8) w/ weighted sumTraining Set=LibriMix, Training hours=460 hours, Mix Type=mixboth: speech + noise, Overlap Mode=max, Training weights (λasr, λdiar, λsep)=(0.1, 0.1, 0.8), Weighted Sum=true2025.0825.5