A comparative study of noise estimation algorithms for nonlinear compensation in robust speech recognition

2017 ◽  
Vol 89 ◽  
pp. 58-69
Author(s):  
Yong Zhao ◽  
Biing-Hwang (Fred) Juang
Keyword(s):  
Speech Recognition ◽  
Comparative Study ◽  
Noise Estimation ◽  
Robust Speech Recognition ◽  
Estimation Algorithms ◽  
Nonlinear Compensation

MODIFIED QUANTILE BASED ONLINE NOISE ADAPTATION METHOD FOR A ROBUST SPEECH RECOGNITION INTERFACE

2007 ◽  
Vol 21 (04) ◽  
pp. 759-772
Author(s):  
HEUNGKYU LEE ◽  
JUNE KIM
Keyword(s):  
Speech Recognition ◽  
Estimation Method ◽  
Estimation Procedure ◽  
Gaussian Mixture ◽  
Noise Estimation ◽  
Noise Model ◽  
Robust Speech Recognition ◽  
Model Adaptation ◽  
Speech Database ◽  
Adaptation Method

This paper proposes the online noise model adaptation technique using the modified quantile based noise estimation method for feature compensation of noisy speech that is based on the Gaussian mixture model for a robust speech recognition interface in real car environments. The proposed method is designed for an active online model adaptation method to cope with varying environmental noise conditions, and enhance speech recognition accuracy. This method is compensated on logarithmic filter-bank energies domain, and modified quantile based noise estimation method using beta-order harmonic mean is employed to the online noise estimation procedure. Experimental evaluation is done by using Aurora 2 speech database, and robust results were obtained than from other comparative algorithms.

Sign in / Sign up

Export Citation Format

Share Document