Single channel multi-talker speech separation with deep learning

The objective of speech separation is to divide a mixture signal, i.e., multiple speakers with background noise, into a set of individual streams, where each stream only contains a single speaker's voice. The study of speech separation is important as the performance of speech applications degr...

Volledige beschrijving

Bibliografische gegevens
Hoofdauteur: Xu, Chenglin
Andere auteurs: Chng Eng Siong
Formaat: Thesis-Doctor of Philosophy
Taal:English
Gepubliceerd in: Nanyang Technological University 2020
Onderwerpen:
Online toegang:https://hdl.handle.net/10356/143903