Show simple item record

dc.contributorUniversitat Ramon Llull. La Salle
dc.contributor.authorFreixes Guerreiro, Marc
dc.contributor.authorAlías Pujol, Francesc
dc.contributor.authorSocoró Carrié, Joan Claudi
dc.date.accessioned2020-03-27T15:11:35Z
dc.date.accessioned2023-10-02T06:42:13Z
dc.date.available2020-03-27T15:11:35Z
dc.date.available2023-10-02T06:42:13Z
dc.date.created2019
dc.date.issued2019-12
dc.identifier.urihttp://hdl.handle.net/20.500.14342/3421
dc.description.abstractText-to-speech (TTS) synthesis systems have been widely used in general-purpose applications based on the generation of speech. Nonetheless, there are some domains, such as storytelling or voice output aid devices, which may also require singing. To enable a corpus-based TTS system to sing, a supplementary singing database should be recorded. This solution, however, might be too costly for eventual singing needs, or even unfeasible if the original speaker is unavailable or unable to sing properly. This work introduces a unit selection-based text-to-speech-and-singing (US-TTS&S) synthesis framework, which integrates speech-to-singing (STS) conversion to enable the generation of both speech and singing from an input text and a score, respectively, using the same neutral speech corpus. The viability of the proposal is evaluated considering three vocal ranges and two tempos on a proof-of-concept implementation using a 2.6-h Spanish neutral speech corpus. The experiments show that challenging STS transformation factors are required to sing beyond the corpus vocal range and/or with notes longer than 150 ms. While score-driven US configurations allow the reduction of pitch-scale factors, time-scale factors are not reduced due to the short length of the spoken vowels. Moreover, in the MUSHRA test, text-driven and score-driven US configurations obtain similar naturalness rates of around 40 for all the analysed scenarios. Although these naturalness scores are far from those of vocaloid, the singing scores of around 60 which were obtained validate that the framework could reasonably address eventual singing needs.eng
dc.format.extent14 p.
dc.language.isoeng
dc.publisherSpringerLink
dc.relation.ispartofEURASIP Journal on Audio, Speech, and Music Processing. 2019:22
dc.rights© L'autor/a
dc.rightsAttribution 4.0 International
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.sourceRECERCAT (Dipòsit de la Recerca de Catalunya)
dc.subject.otherParla
dc.titleA unit selection text-to-speech-and-singing synthesis framework from neutral speech: proof of concept
dc.typeinfo:eu-repo/semantics/article
dc.typeinfo:eu-repo/semantics/publishedVersion
dc.rights.accessLevelinfo:eu-repo/semantics/openAccess
dc.embargo.termscap
dc.subject.udc78
dc.identifier.doihttps://doi.org/10.1186/s13636-019-0163-y
dc.relation.projectIDinfo:eu-repo/grantAgreement/MINECO i FEDER/PN I+D Excelencia/TEC2016-81107-P
dc.relation.projectIDinfo:eu-repo/grantAgreement/SUR del DEC i FSE/FI/2016FI_B2 00094
dc.relation.projectIDinfo:eu-repo/grantAgreement/URL i La Caixa/Intensificació recerca PDI/2018-URL-IR1rQ-021
dc.relation.projectIDinfo:eu-repo/grantAgreement/URL i La Caixa/Intensificació recerca PDI/2018-URL-IR2nQ-029


Files in this item

 

This item appears in the following Collection(s)

Show simple item record

© L'autor/a
Except where otherwise noted, this item's license is described as http://creativecommons.org/licenses/by/4.0/
Share on TwitterShare on LinkedinShare on FacebookShare on TelegramShare on WhatsappPrint