A Speaker-Dependent Approach to Separation of Far-Field Multi-Talker Microphone Array Speech for Front-End Processing in the CHiME-5 Challenge

Lei Sun (孙雷)

[0]

Jun Du

[0]

[0]

[0]

[0]

[0]

pp. 827-840, 2019.

Cited by: 0|Views46

EI WOS

Keywords:

Speech recognitionSpeech enhancementMicrophonesArraysArray signal processingMore(1+)

Abstract:

We propose a novel speaker-dependent speech separation framework for the challenging CHiME-5 acoustic environments, exploiting advantages of both deep learning based and conventional preprocessing techniques to prepare data effectively for separating target speech from multi-talker mixed speech collected with multiple microphone arrays. F...More

Code:

Data:

Get fulltext within 24h

View via Publisher