Multi-Condition Training for Unknown Environment Adaptation in Robust ASR Under Real Conditions

Multi-Condition Training for Unknown Environment Adaptation in Robust ASR Under Real Conditions

Automatic speech recognition (ASR) systems frequently work in a noisy environment. As they are often trained on clean speech data, noise reduction or adaptation techniques are applied to decrease the influence of background disturbance even in the case of unknown conditions. Speech data mixed with n...

Full description

Bibliographic Details
Main Author: J. Rajnoha
Format: Article
Language:English
Published: CTU Central Library 2009-01-01
Series:Acta Polytechnica
Subjects:
speech recognition
environment adaptation
spectral subtraction
MLLR
noisy background
Online Access:https://ojs.cvut.cz/ojs/index.php/ap/article/view/1105

Internet

https://ojs.cvut.cz/ojs/index.php/ap/article/view/1105

Similar Items