Efficient time-domain speech separation using short encoded sequence network

The key to single-channel time-domain speech separation lies in encoding the mixed speech into latent feature representations by encoder and obtaining the accurate estimation of the target speaker masks by the separation network. Despite the advanced separation network contribute to separate target...

Full description

Bibliographic Details

Published in:	Speech communication Vol. 166; p. 103150
Main Authors:	Liu, Debang, Zhang, Tianqi, Christensen, Mads Græsbøll, Ma, Baoze, Deng, Pan
Format:	Journal Article
Language:	English
Published:	Elsevier B.V 01.01.2025
Subjects:	Computational complexity Multi-temporal resolution Transformer Short sequence encoder–decoder framework Speech separation Speech separation Computational complexity Multi-temporal resolution Transformer Short sequence encoder–decoder framework
ISSN:	0167-6393
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!