IMPROVED SYLLABLE-BASED CONTINUOUS MANDARINE SPEECH RECOGNITION USING INTERSYLLABLE BOUNDARY MODELS

Full metadata record

DC Field	Value	Language
dc.contributor.author	CHANG, S	en_US
dc.contributor.author	CHEN, SH	en_US
dc.date.accessioned	2014-12-08T15:03:22Z	-
dc.date.available	2014-12-08T15:03:22Z	-
dc.date.issued	1995-05-25	en_US
dc.identifier.issn	0013-5194	en_US
dc.identifier.uri	http://dx.doi.org/10.1049/el:19950629	en_US
dc.identifier.uri	http://hdl.handle.net/11536/1914	-
dc.description.abstract	A novel approach to compensate for the intersyllable coarticulation effect on continuous Mandarin speech recognition by supplementing the syllable HMM models with intersyllable boundary models is proposed. Experimental results show that the syllable recognition errors of a speaker-dependent recognition task are reduced by 24%.	en_US
dc.language.iso	en_US	en_US
dc.subject	SPEECH RECOGNITION	en_US
dc.title	IMPROVED SYLLABLE-BASED CONTINUOUS MANDARINE SPEECH RECOGNITION USING INTERSYLLABLE BOUNDARY MODELS	en_US
dc.type	Article	en_US
dc.identifier.doi	10.1049/el:19950629	en_US
dc.identifier.journal	ELECTRONICS LETTERS	en_US
dc.citation.volume	31	en_US
dc.citation.issue	11	en_US
dc.citation.spage	853	en_US
dc.citation.epage	854	en_US
dc.contributor.department	電信工程研究所	zh_TW
dc.contributor.department	電信研究中心	zh_TW
dc.contributor.department	Institute of Communications Engineering	en_US
dc.contributor.department	Center for Telecommunications Research	en_US
dc.identifier.wosnumber	WOS:A1995RC65600010	-
dc.citation.woscount	1	-
Appears in Collections:	Articles

Files in This Item:

If it is a zip file, please download the file and unzip it, then open index.html in a browser to view the full text content.