Automatic speech segmentation based on HMM

Simple item page
dc.contributor.authorKroul, Martin
dc.date.accessioned2016-05-24
dc.date.available2016-05-24
dc.date.issued2007
dc.description.abstractThis contribution deals with the problem of automatic phoneme segmentation using HMMs. Auto-matization of speech segmentation task is important for applications, where large amount of data is needed to process, so manual segmentation is out of the question. In this paper we focus on automatic segmentation of re-cordings, which will be used for triphone synthesis unit database creation. For speech synthesis, the speech unit quality is a crucial aspect, so the maximal accuracy in segmentation is needed here. In this work, different kinds of HMMs with various parameters have been trained and their usefulness for automatic segmentation is discussed. At the end of this work, some segmentation accuracy tests of all models are presented.en
dc.formattext
dc.identifier.issn1210-2512
dc.identifier.scopus2-s2.0-84904503298
dc.identifier.urihttps://dspace.tul.cz/handle/15240/16337
dc.identifier.urihttps://www.radioeng.cz/fulltexts/2007/07_02_56_61.pdf
dc.language.isoen
dc.publisherTechnická Univerzita v Libercics
dc.publisherTechnical university of Liberec, Czech Republicen
dc.publisher.abbreviationTUL
dc.relation.ispartofRadioengineeringen
dc.sourcej-scopusen
dc.sourcej-woken
dc.subjectalignmenten
dc.subjectAutomatic segmentationen
dc.subjectHMMen
dc.subjectMonophonesen
dc.subjectSpeech databaseen
dc.subjectSpeech processingen
dc.subjectTriphonesen
dc.titleAutomatic speech segmentation based on HMMen
dc.typeArticleen
local.accessopen
local.citation.epage61
local.citation.spage56
local.facultyInstitute of Information Technology and Electronics
local.fulltextyes
local.identifier.stagRIV/46747885:24220/07:#0000401
local.identifier.wok255863300010
local.relation.issue2
local.relation.volume16
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Kroul.pdf
Size:
121.11 KB
Format:
Adobe Portable Document Format
Description:
Článek
Download
Collections