A neuro-fuzzy approach to speech recognition without time alignment

機構典藏 > College of Engineering > Graduate Institute & Department of Electrical Engineering > Journal Article > Item 987654321/46169

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/46169

Title:	A neuro-fuzzy approach to speech recognition without time alignment
Authors:	蘇木春;Su, Mu-chun;Hsieh, Ching-tang;Chin, Chieh-ching
Contributors:	淡江大學電機工程學系
Keywords:	Speech recognition;Neural networks;Pattern recognition;Expert system;Membership function
Date:	1998-08-16
Issue Date:	2010-03-26 21:07:54 (UTC+8)
Publisher:	Medwell Journals
Abstract:	Several successful approaches to speech recognition have been proposed. Most of them involve time alignment which requires substantial computation and considerable memory storage. In this paper, we present a neuro-fuzzy approach to speech recognition without time alignment. This approach is a powerful method for selecting reference templates; therefore, considerable memory storage is alleviated. In addition, it greatly reduces substantial computation in the matching process because it obviates time alignment. Base on this approach, a Mandarin speech recognition system without time alignment is implemented. Two databases were utilized for verifying its performance. An encouraging experimental result confirms the effectiveness of the proposed neuro-fuzzy approach to speech recognition without time alignment.
Relation:	Fuzzy Sets and Systems 98(1), pp.33-41
DOI:	10.1016/S0165-0114(96)00375-2
Appears in Collections:	[Graduate Institute & Department of Electrical Engineering] Journal Article

Files in This Item:

File	Size	Format
	0Kb	Unknown	378	View/Open