Presentation	1995/9/12 Japanese Vowels Recognition using Principal Component Analysis Yukio Mori, Naoyuki Aikawa,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	In this paper, we have extracted and recognized Japanese vowels in speaker-independent speech using principal component analysis. By principal component analysis for short-time spectrum envelopes of vowels, we can get distribution patterns of principal component scores. Some of these patterns tend to form a group of each vowels. We can determine a candidate of vowels from comparing distribution patterns of principal component scores of any vowels with known ones. In this paper, we get 91.4% recognition rate for evaluation of any samples (5 vowels by 14 speakers) by known samples (5 vowels by 40 speakers).
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Vowel recognition / Speaker-independent speech recognition / Principal component analysis
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)	Japanese Vowels Recognition using Principal Component Analysis
Sub Title (in English)
Keyword(1)	Vowel recognition
Keyword(2)	Speaker-independent speech recognition
Keyword(3)	Principal component analysis
1st Author's Name	Yukio Mori
1st Author's Affiliation	Department of Electronics and Communication, Salesian Polytechnic()
2nd Author's Name	Naoyuki Aikawa
2nd Author's Affiliation	Department of Electrical engineering, Faculty of Technology, Tokyo Metropolitan University
Date	1995/9/12
Paper #
Volume (vol)	vol.95
Number (no)	227
Page	pp.pp.-
#Pages	6
Date of Issue