Applying spectral normalisation and efficient envelope estimation and statistical transformation for the voice conversion challenge 2016
Mostra el registre complet Registre parcial de l'ítem
- dc.contributor.author Villavicencio, Fernandoca
- dc.contributor.author Yamagishi, Junichica
- dc.contributor.author Bonada, Jordi, 1973-ca
- dc.contributor.author Espic, Felipeca
- dc.date.accessioned 2017-10-10T08:14:24Z
- dc.date.available 2017-10-10T08:14:24Z
- dc.date.issued 2016
- dc.description Comunicació presentada a l'Interspeech 2016, celebrat els dies 8 a 12 de setembre de 2016 a San Francisco, California.
- dc.description.abstract In this work we present our entry for the Voice Conversion Challenge 2016, denoting new features to previous work on GMM-based voice conversion. We incorporate frequency warping and pitch transposition strategies to perform a normalisation of the spectral conditions, with benefits confirmed by objective and perceptual means. Moreover, the results of the challenge showed our entry among the highest performing systems in terms of perceived naturalness while maintaining the target similarity performance of GMM-based conversion.en
- dc.format.mimetype application/pdfca
- dc.identifier.citation Villavicencio F, Yamagishi J, Bonada J, Espic F. Applying spectral normalisation and efficient envelope estimation and statistical transformation for the voice conversion challenge 2016. In: Interspeech 2016; 2016 Sep 08-12; San Francisco (CA). [Baixas]: ISCA; 2016. p. 1657-61. DOI: 10.21437/Interspeech.2016-305
- dc.identifier.doi http://dx.doi.org/10.21437/Interspeech.2016-305
- dc.identifier.uri http://hdl.handle.net/10230/32891
- dc.language.iso eng
- dc.publisher International Speech Communication Association (ISCA)ca
- dc.relation.ispartof Interspeech 2016; 2016 Sep 08-12; San Francisco (CA). [Baixas]: ISCA; 2016. p. 1657-61.
- dc.rights © 2016 ISCA
- dc.rights.accessRights info:eu-repo/semantics/openAccess
- dc.subject.keyword Voice conversionen
- dc.subject.keyword Speech synthesis
- dc.subject.keyword Statistical spectral transformationen
- dc.subject.keyword Spectral envelope modelingen
- dc.title Applying spectral normalisation and efficient envelope estimation and statistical transformation for the voice conversion challenge 2016ca
- dc.type info:eu-repo/semantics/conferenceObject
- dc.type.version info:eu-repo/semantics/publishedVersion