most citedMossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions

1 citations · 1 across the 2 of their papers we have counts for

collaborators

2 papers

cs.SD2023

D2Former: A Fully Complex Dual-Path Dual-Decoder Conformer Network using Joint Complex Masking and Complex Spectral Mapping for Monaural Speech Enhancement

Shengkui Zhao, Bin Ma

Monaural speech enhancement has been widely studied using real networks in the time-frequency (TF) domain. However, the input and the target are naturally complex-valued in the TF…

cs.SD2023★ 1 cited

MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions

Shengkui Zhao, Bin Ma

Transformer based models have provided significant performance improvements in monaural speech separation. However, there is still a performance gap compared to a recent proposed u…