Speech Enhancement Based on Blind Source Separation in Car Environments


NAIST \| Library	Advanced Search	Japanese \| English

Please use this identifier to cite or link to this item: http://hdl.handle.net/10061/8090

Title:	Speech Enhancement Based on Blind Source Separation in Car Environments
Authors:	Hiroshi Saruwatari Katsuyuki Sawai Tsuyoki Nishikawa Akinobu Lee Kiyohiro Shikano Atsunobu Kaminuma Masao Sakata Daisuke Saitoh
Issue Date:	Apr-2005
Publisher:	IEEE
Start page:	1205
End page:	1212
Abstract:	This paper describes a new speech enhancement system used in car environments, where independent component analysis (ICA)-based blind source separation (BSS) and subband elimination (SBE) processing are combined to achieve a high separation performance. The proposed method consists of two parts, fast-convergence frequency domain ICA and SBE processing based on the independence among the separated subband signals. The SBE enforcedly eliminates the subband components in which the separation could not be performed well. The experiment in a real car environment reveals that the proposed method can improve the qualities of the separated speech and word recognition rates for both directional and diffuse noises.
Description:	ICDE2005: the 21st International Conference on Data Engineering: International Workshop on Realworld Multimedia Corpora in Mobile Environment (RWCinME2005), April 5-8, 2005, Tokyo, Japan.
URI:	http://hdl.handle.net/10061/8090
ISBN:	0769526578
Rights:	Copyright 2005 IEEE
Text Version:	Publisher
Publisher DOI:	10.1109/ICDE.2005.289
Appears in Collections:	情報科学研究科 / Graduate School of Information Science

Files in This Item:

File	Size	Format
ICDE_2005_1205.pdf	1.44 MB	Adobe PDF	View/Open