The use of pitch in Large-Vocabulary Continuous Speech Recognition System

Please use this identifier to cite or link to this item: https://elib.belstu.by/handle/123456789/24541

Full metadata record

DC Field	Value	Language
dc.contributor.author	Płonkowski, Marcin	-
dc.contributor.author	Urbanovich, P. P.	-
dc.date.accessioned	2018-03-04T09:54:57Z	-
dc.date.available	2018-03-04T09:54:57Z	-
dc.date.issued	2016	-
dc.identifier.citation	Płonkowski, M. The use of pitch in Large-Vocabulary Continuous Speech Recognition System / M.Płonkowski, P. Urbanovich // PRZEGLĄD ELEKTROTECHNICZNY. - 2016. -№ 8.- p. 78-81.	ru
dc.identifier.uri	https://elib.belstu.by/handle/123456789/24541	-
dc.description	In this article the authors normalize the speech signal based on the publicly available AN4 database. The authors added to the algorithm of calculating the MFCC coefficients, the normalization procedure, that uses pitch of the voice. As demonstrated by empirical tests authors were able to improve speech recognition accuracy rate of about 20%.	ru
dc.subject	speech recognition	ru
dc.subject	CMU Sphinx	ru
dc.subject	speech normalization	ru
dc.subject	pitch	ru
dc.title	The use of pitch in Large-Vocabulary Continuous Speech Recognition System	ru
dc.type	Article	ru
dc.identifier.DOI	doi:10.15199/48.2016.08.21	-
Appears in Collections:	Публикации в зарубежных изданиях

Files in This Item:

File	Description	Size	Format
Plon_Urb1.PDF		286.19 kB	Adobe PDF	View/Open