Presentation 2004/6/18
Date Dependent Filtering for Noisy Speech Signal
Takaaki ISHIDA, Akira TAGUCHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Many conventional speech noise removal methods are performed by time invariant filtering. However, the speech signal is consisted of two sections, one is voice section, the other is non-voice section. These two sections are demanded to different methodology each other. In this paper, we propose the data-dependent filtering for removing the additive noise from speech signal. The data-dependent filtering realizes the noise removing sufficiently in non-voice section, while preserving the speech signal in voice section. We show the effectiveness of the proposed method compared to the conventional method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Speech signal / Data-dependent filtering / noise removal / voice section / non-voice section
Paper # SIS2004-7
Date of Issue

Conference Information
Committee SIS
Conference Date 2004/6/18(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Smart Info-Media Systems (SIS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Date Dependent Filtering for Noisy Speech Signal
Sub Title (in English)
Keyword(1) Speech signal
Keyword(2) Data-dependent filtering
Keyword(3) noise removal
Keyword(4) voice section
Keyword(5) non-voice section
1st Author's Name Takaaki ISHIDA
1st Author's Affiliation Faculty of Engineering, Musashi Institute of Technology()
2nd Author's Name Akira TAGUCHI
2nd Author's Affiliation Faculty of Engineering, Musashi Institute of Technology
Date 2004/6/18
Paper # SIS2004-7
Volume (vol) vol.104
Number (no) 144
Page pp.pp.-
#Pages 6
Date of Issue