WSJ-0-2/3mix

The 'WSJ0-2/3mix' dataset/benchmark contains mixed speech signals from the Wall Street Journal corpus and is used to evaluate the performance of algorithms in monaural speech separation.

Papers using WSJ-0-2/3mix (4)

Exploring Self-attention Mechanisms For Speech Separation2022 · 46 citesTiny-sepformer: A Tiny Time-domain Transformer Network For Speech Separation2022 · 14 citesMossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation2023 · 1 citesTiny-Sepformer: A Tiny Time-Domain Transformer Network for Speech Separation2022