Improved Two-stage Wiener Filter for Robust Speaker Identification

In order to solve the problem of robustness in text-independent speaker identification, two-stage Wiener filter presented in the ETSI standard is used in this paper. However, the performance of the voice activity detection (VAD) block in the standard is not so satisfying under lower SNR. Thus constr...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanlu Xie, Minghui Liu, Zhiqiang Yao, Beiqian Dai
Format: Conference Proceeding
Language:English
Subjects:
Additive noise
Automatic speech recognition
Degradation
Noise reduction
Noise robustness
Speech enhancement
Telecommunication standards
Vector quantization
White noise
Wiener filter
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In order to solve the problem of robustness in text-independent speaker identification, two-stage Wiener filter presented in the ETSI standard is used in this paper. However, the performance of the voice activity detection (VAD) block in the standard is not so satisfying under lower SNR. Thus constrained-clustering vector quantization is presented to improve the block in the Wiener filter method. Experiments based on the MSRA's Mandarin speech corpora show the good robustness of the improved method to several common additive noises
ISSN:1051-4651
2831-7475
DOI:10.1109/ICPR.2006.696