Presentation	1996/7/19 A Speech Enhancement Technique using Array Processing based on the Coherent Subspace Method Futohi Asano,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	When using speech recognition system in noisy environments, a speech enhancement technique, that reduces the environmental noise and recovers speech spectrum, is indispensable. In this report, a method, that recovers the LPC-spectrum of speech from noisy microphone array inputs, is proposed. This method is especially suitable for reducing omni-directional noise such as background noise. The method is rased on the coherent subspace method established in the direction-of-arrival (DOA) estimation. Noise is reduced by eliminating the subspace where the contributtion of the target speech signal is small. Simulation results show that some pcaks of formants, those were could not be estimated by the conventional delay-and-sum beamformer, were clearly estimated by the proposed method.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Microphone array / LPC spectrum / Noise reduction / Coherent Subspace / Projection
Paper #	EA96-25
Date of Issue

Conference Information
Committee	EA
Conference Date	1996/7/19(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	Engineering Acoustics (EA)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	A Speech Enhancement Technique using Array Processing based on the Coherent Subspace Method
Sub Title (in English)
Keyword(1)	Microphone array
Keyword(2)	LPC spectrum
Keyword(3)	Noise reduction
Keyword(4)	Coherent Subspace
Keyword(5)	Projection
1st Author's Name	Futohi Asano
1st Author's Affiliation	Electrotechnical Laboratory()
Date	1996/7/19
Paper #	EA96-25
Volume (vol)	vol.96
Number (no)	162
Page	pp.pp.-
#Pages	8
Date of Issue