Robust features for speech recognition using minimum variance distortionless response (MVDR) spectrum estimation and feature normalization techniques
Resource
Chinese Spoken Language Processing, 2004 International Symposium on
Journal
2004 International Symposium on Chinese Spoken Language Processing
Pages
101-104
Date Issued
2004-12
Date
2004-12
Author(s)
Chen, Yi
DOI
N/A
Abstract
In this paper, feature extraction methods based on frequency-warped minimum variance distortionless response (MVDR) spectrum estimation are analyzed and tested. The effectiveness of the conventional FFT-based mel-frequency cepstrum coefficients (MFCC) and the MVDR-based features are carefully compared. Two normalization techniques are further applied to improve the robustness of the features: the widely used cepstral normalization (CN), and newly proposed progressive histogram equalization (PHEQ). Extensive experiments with respect to the AURORA2 database were performed. The results indicated that both the MVDR-based features and the normalization processes are very helpful.
Type
journal article
File(s)![Thumbnail Image]()
Loading...
Name
01409596.pdf
Size
331.18 KB
Format
Adobe PDF
Checksum
(MD5):b15dc56a51b7068dee53d37a95a577f4