GMM classification of text-to-speech synthesis: identification of original speaker’s voice

Show simple item record
dc.contributor.authorPřibil, Jiří
dc.contributor.authorPřibilová, Anna
dc.contributor.authorMatoušek, Jindřich
dc.date.accessioned2017-05-30T06:57:42Z
dc.date.available2017-05-30T06:57:42Z
dc.date.issued2014
dc.description.abstract-translatedThis paper describes two experiments. The first one deals with evaluation of synthetic speech quality by reverse identification of original speakers whose voices had been used for several Czech text-to-speech (TTS) systems. The second experiment was aimed at evaluation of the influence of voice transformation on the original speaker recognition. The paper further describes an analysis of the influence of initial settings for creation and training of the Gaussian mixture models (GMM), and the influence of different types of used speech features (spectral and/or supra-segmental) on correctness of GMM identification. The stability of the identification process with respect to the duration of the tested sentence (number of the processed frames) was analysed, too.en
dc.format9 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.citationPĹIBIL, Jiří; PĹIBILOVĂ, Anna; MATOUĹ EK, JindĹ™ich. GMM classification of text-to-speech synthesis: identification of original speaker’s voice. In: Text, speech and dialogue. Berlin: Springer, 2014, p. 365-373. (Lecture notes in artificial intelligence; 8655). ISBN 978-3-319-10815-5.en
dc.identifier.doi10.1007/978-3-319-10816-2_44
dc.identifier.isbn978-3-319-10815-5
dc.identifier.issn0302-9743
dc.identifier.urihttp://hdl.handle.net/11025/26010
dc.language.isoenen
dc.publisherSpringercs
dc.relation.ispartofseriesLecture notes in artificial intelligence; 8655en
dc.rights© Springeren
dc.rights.accessopenAccessen
dc.subjectsyntéza řečics
dc.subjectGMM klasifikacecs
dc.subjectstatistická analýzacs
dc.subject.translatedspeech synthesisen
dc.subject.translatedGMM classificationen
dc.subject.translatedstatistical analysisen
dc.titleGMM classification of text-to-speech synthesis: identification of original speaker’s voiceen
dc.title.alternativeKlasifikace syntézy řeči z textu pomocí GMM: Identifikace původního hlasu řečníkacs
dc.typečlánekcs
dc.typearticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
Pribil.pdf
Size:
569.11 KB
Format:
Adobe Portable Document Format
Description:
Plný text
Download
License bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Articles (KIV)