MossFormer (M) + DM

Reported on 2 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Speech2 results

Speech SeparationonWSJ0-2mix
SI-SDRi· 2023-02-23
22.5
best: 25.1 (TF-Locoformer (L) + DM)
MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions arXiv:2302.11824
Speech SeparationonWSJ0-3mix
SI-SDRi· 2023-02-23
20.8
best: 23.7 (SepTDA)
MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions arXiv:2302.11824