Two-domain feature compensation for robust speech recognition

Authors:
Haifeng Shen;Gang Liu;Jun Guo;Qunxia Li
Affiliations:
Beijing University of Posts and Telecommunications, Beijing, China;Beijing University of Posts and Telecommunications, Beijing, China;Beijing University of Posts and Telecommunications, Beijing, China;University of Science and Technology Beijing, Beijing, China
Venue:
ISNN'05 Proceedings of the Second international conference on Advances in neural networks - Volume Part II
Year:
2005

Citing 2
Cited 6

Speech recognition in noisy environments using first-order vector Taylor series

Speech Communication
Speech recognition in noisy environments

Speech recognition in noisy environments

Model-Based Feature Compensation for Robust Speech Recognition

Fundamenta Informaticae
Mixed environment compensation based on maximum a posteriori estimation for robust speech recognition

Artificial Intelligence Review
Non-stationary environment compensation using sequential EM algorithm for robust speech recognition

PKDD'05 Proceedings of the 9th European conference on Principles and Practice of Knowledge Discovery in Databases
HMM parameter adaptation using the truncated first-order VTS and EM algorithm for robust speech recognition

CIS'05 Proceedings of the 2005 international conference on Computational Intelligence and Security - Volume Part I
Environment compensation based on maximum a posteriori estimation for improved speech recognition

MICAI'05 Proceedings of the 4th Mexican international conference on Advances in Artificial Intelligence
Model-Based Feature Compensation for Robust Speech Recognition

Fundamenta Informaticae

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we develop a two-domain feature compensation approach to the log-filterbank and log-energy features for reducing the effects of noise. The environment model is approximated by statistical linear approximation (SLA) function. The cepstral and log-energy feature vectors of the clean speech are trained by using the Self-Organizing Map (SOM) neural network with the assumption that the speech can be well represented as multivariate diagonal Gaussian mixtures model (GMM). With the effective training of clean speech and environment model approximation, noise statistics is well estimated using batch-EM algorithm in a maximum likelihood (ML) sense. Experiments in the large vocabulary speaker-independent continuous speech recognition demonstrate that this approach exhibits a noticeable performance.