Using hierarchical information structure for prosody prediction in content-to-speech applications

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Domínguez Bajo, Mónicaca
• dc.contributor.author Farrús, Mireiaca
• dc.contributor.author Burga Díaz, Aliciaca
• dc.contributor.author Wanner, Leoca
• dc.date.accessioned 2016-12-13T16:52:11Z
• dc.date.available 2016-12-13T16:52:11Z
• dc.date.issued 2016ca
• dc.description Paper presented at Speech Prosody 8, 2016 May 31 - Jun 3; Boston, United States.en
• dc.description.abstract State-of-the-art prosody modelling in content-to-speech (CTS) applications still uses the same methodology to predict intonation cues as text-to-speech (TTS) applications, namely the analysis of the generated surface sentences with respect to part of speech, syntactic dependency relations and word order. On the other side, several theoretical studies argue that morphology, syntax, and information (or communicative) structure that organizes/na given content (semantic or deep-syntactic structure) with respect to the intention of the speaker show a strong correlation with intonation. However, little empirical work based on sufficiently large corpora has been carried out so far to buttress this argumentation. We present empirical evidence for the Information Structure–Prosody correlation using the Wall Street Journal Penn Treebank corpus recorded by native American English speakers. Our experiments reach a prosody prediction accuracy of 80% using the hierarchical information structure from the Meaning-Text Theory, compared to 59% of the baseline.en
• dc.description.sponsorship This work is part of a project that has received funding from the European Union’s Horizon 2020 Research and Innovation/nProgramme under the Grant Agreement number H2020-RIA-645012. The second author is partially funded by a grant from/nthe Spanish Ministry of Economy and Competitivity in the framework of the Juan de la Cierva fellowship program.en
• dc.format.mimetype application/pdfca
• dc.identifier.citation Domínguez M, Farrús M, Burga A, Wanner L. Using hierarchical information structure for prosody prediction in content-to-speech application. In: Proceedings of Speech Prosody 8; 2016 May 31 - Jun 3; Boston, United States. [Boston]: ISCA, 2016. p. 1019-23. DOI: 10.21437/SPEECHPROSODY.2016-209en
• dc.identifier.doi http://dx.doi.org/10.21437/SPEECHPROSODY.2016-209
• dc.identifier.issn 2333-2042ca
• dc.identifier.uri http://hdl.handle.net/10230/27753
• dc.language.iso engca
• dc.publisher International Speech Communication Association (ISCA)ca
• dc.relation.ispartof Proceedings of Speech Prosody 8; 2016 May 31 - Jun 3; Boston, United States. [Boston]: ISCA, 2016. p. 1019-23.
• dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/645012ca
• dc.rights © ISCA. The authors retain the rights to any intellectual property developed by the authors and included in the manuscript.ca
• dc.rights.accessRights info:eu-repo/semantics/openAccessca
• dc.subject.keyword Information structureen
• dc.subject.keyword Thematicityen
• dc.subject.keyword Themeen
• dc.subject.keyword Rhemeen
• dc.subject.keyword Prosodyen
• dc.subject.keyword Prosodic phraseen
• dc.subject.keyword ToBIen
• dc.title Using hierarchical information structure for prosody prediction in content-to-speech applicationsca
• dc.type info:eu-repo/semantics/conferenceObjectca
• dc.type.version info:eu-repo/semantics/publishedVersionca