Subband-based blind signal separation for noisy speech recognition

被引：36

作者：

Park, HM

Jung, HY

Lee, TW

Lee, SY

机构：

[1] Korea Adv Inst Sci & Technol, Dept Elect Engn, Yusong Gu, Taejon 305701, South Korea

[2] Korea Adv Inst Sci & Technol, Brain Sci Res Ctr, Yusong Gu, Taejon 305701, South Korea

[3] Salk Inst, Computat Neurobiol Lab, La Jolla, CA 92037 USA

[4] Univ Calif San Diego, Inst Neural Computat, San Diego, CA 92103 USA

来源：

ELECTRONICS LETTERS | 1999年 / 35卷 / 23期

关键词：

D O I：

10.1049/el:19991358

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

A method for directly extracting clean speech features from noisy speech is proposed. This process is based on independent component analysis (ICA) and a new feature analysis technique for reducing the computational complexity of the frequency-domain ICA. For noisy speech signals recorded in real environments, this method yielded a considerable performance improvement.

引用

页码：2011 / 2012

页数：2