CATOTRON – A Neural text-to-speech system in catalan

Külebi, Baybars; Öktem, Alp; Peiró Lilja, Àlex; Pascual, Santiago; Farrús, Mireia

Home
→
Recerca: articles, congressos, llibres
→
Departament de Tecnologies de la Informació i les Comunicacions
→
Congressos (Departament de Tecnologies de la Informació i les Comunicacions)
→
View Item

dc.contributor.author	Külebi, Baybars
dc.contributor.author	Öktem, Alp
dc.contributor.author	Peiró Lilja, Àlex
dc.contributor.author	Pascual, Santiago
dc.contributor.author	Farrús, Mireia
dc.date.accessioned	2020-11-11T07:30:29Z
dc.date.available	2020-11-11T07:30:29Z
dc.date.issued	2020
dc.identifier.citation	Külebi B, Öktem A, Peiró-Lilja A, Pascual S, Farrús M. CATOTRON – A Neural text-to-speech system in catalan. In: Proceedings of Interspeech 2020; 2020 Oct 25-29; Shanghai, China. [Baixas]: ISCA; 2020. p. 490-1.
dc.identifier.issn	1990-9772
dc.identifier.uri	http://hdl.handle.net/10230/45715
dc.description	Comunicació presentada a Interspeech 2020 celebrat del 25 al 29 d'octubre de 2020 a Shanghai, Xina.
dc.description.abstract	We present Catotron, a neural network-based open-source speech synthesis system in Catalan. Catotron consists of a sequence-to-sequence model trained with two small opensource datasets based on semi-spontaneous and read speech. We demonstrate how a neural TTS can be built for languages with limited resources using found-data optimization and crosslingual transfer learning. We make the datasets, initial models and source code publicly available for both commercial and research purposes.
dc.description.sponsorship	This work was subsidised by the Catalan Department of Culture. A part of the funding comes from the financing administered by the inheritance board of the Generalitat de Catalunya. The last author has been funded by the Agencia Estatal de Investigaci ´on (AEI), Ministerio de Ciencia, Innovaci´on y Universidades and the Fondo Social Europeo (FSE) under grant RYC- 2015-17239 (AEI/FSE, UE). Part of this work has been carried out using an NVIDIA GPU Titan Xp generously provided by NVIDIA Company. This research was also partially supported by the project TEC2015-69266-P (MINECO/FEDER, UE).
dc.format.mimetype	application/pdf
dc.language.iso	eng
dc.publisher	International Speech Communication Association (ISCA)
dc.relation.ispartof	Proceedings of Interspeech 2020; 2020 Oct 25-29; Shanghai, China. [Baixas]: ISCA; 2020.
dc.relation.isreferencedby	http://github.com/CollectivaT-dev/catotron
dc.relation.isreferencedby	http://github.com/CollectivaT-dev/catotron-cpu
dc.relation.isreferencedby	http://catotron.collectivat.cat/
dc.rights	© 2020 ISCA
dc.title	CATOTRON – A Neural text-to-speech system in catalan
dc.type	info:eu-repo/semantics/conferenceObject
dc.subject.keyword	Text-to-speech
dc.subject.keyword	Sequence-to-sequence
dc.subject.keyword	Catalan
dc.relation.projectID	info:eu-repo/grantAgreement/ES/1PE/TEC2015-69266-P
dc.rights.accessRights	info:eu-repo/semantics/openAccess
dc.type.version	info:eu-repo/semantics/publishedVersion