Hongjie Jia

Efficient Monaural Speech Separation with Multiscale Time-Delay Sampling

Recently, the segmented sample-level modeling approach based on Dual-Path Recurrent Neural Network (DPRNN) has been proved to be effective in Monaural Speech Separation (MSS). Many dual-path networks such as Dual-Path Transformer Network (DPTNet), with a series of improvements to DPRNN, have also im…