Presentation	1995/9/12 Noise Reduction using Neural Network and Regression Analysis Hiroshi Kohda, Tadashi Kitamura,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	In general, speech is nonlinearly degraded by noise, affecting the speech spectrum and cepstrum in various ways. In this paper, we discuss noise reduction using a neural network and a regressive analysis. The method using the neural network learns the normalized cepstrum directly. For modeling the effect of noise, the method of regressive analysis quantizes the learning data into a vector before regressive analysis in order to deal with nonlinear change. We use spectral distortion to evaluate this experiment. At most, each mtehod reduces spectral distortion by 2dB.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Regressive Analysis / Noise Reduction / Neural Network
Paper #
Date of Issue

Conference Information
Committee	DSP
Conference Date	1995/9/12(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	Digital Signal Processing (DSP)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Noise Reduction using Neural Network and Regression Analysis
Sub Title (in English)
Keyword(1)	Regressive Analysis
Keyword(2)	Noise Reduction
Keyword(3)	Neural Network
1st Author's Name	Hiroshi Kohda
1st Author's Affiliation	Nagoya Institute of Technology()
2nd Author's Name	Tadashi Kitamura
2nd Author's Affiliation	Nagoya Institute of Technology
Date	1995/9/12
Paper #
Volume (vol)	vol.95
Number (no)	227
Page	pp.pp.-
#Pages	5
Date of Issue