Paragraph-based prosodic cues for speech synthesis applications

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Farrús, Mireiaca
• dc.contributor.author Lai, Catherineca
• dc.contributor.author Moore, Johanna D.ca
• dc.date.accessioned 2016-12-22T18:46:33Z
• dc.date.available 2016-12-22T18:46:33Z
• dc.date.issued 2016ca
• dc.description Paper presented at: Speech Prosody 2016; 2016 May 31-June 3; Boston (MA, USA)en
• dc.description.abstract Speech synthesis has improved in both expressiveness and voice quality in recent years. However, obtaining full expressiveness when dealing with large multi-sentential synthesized discourse is still a challenge, since speech synthesizers do not take into account the prosodic differences that have been observed in discourse units such as paragraphs. The current study validates and extends previous work by analyzing the prosody of paragraph units in a large and diverse corpus of TED Talks using automatically extracted F0, intensity and timing features. In addition, a series of classification experiments was performed in order to identify which features are consistently used to distinguish paragraph breaks. The results show significant differences in prosody related to paragraph position. Moreover, the classification experiments show that boundary features such as pause duration and differences in F0 and intensity levels are the most consistent cues in marking paragraph boundaries. This suggests that these features should be taken into account when generating spoken discourse in order to improve naturalness and expressiveness.en
• dc.description.sponsorship Part of this work has received funding from the EU’s Horizon 2020 Research and Innovation Programme under the GA H2020-RIA-645012. The first author is partially funded by the Spanish Ministry of Economy and Competitivity through the Juan de la Cierva program and a Jos´e Castillejo mobility granten
• dc.format.mimetype application/pdfca
• dc.identifier.citation Farrús M, Lai C, Moore JD. Paragraph-based prosodic cues for speech synthesis applications. In: Barnes J, Brugos A, Shattuck-Hufnagel S, Veilleux N, editors. Speech Prosody 2016; 2016 May 31-June 3; Boston (MA, USA). [place unknown]: International Speech Communication Association; 2016. p. 1143-7. DOI: 10.21437/SpeechProsody.2016-235ca
• dc.identifier.doi http://dx.doi.org/10.21437/SpeechProsody.2016-235
• dc.identifier.issn 2333-2042ca
• dc.identifier.uri http://hdl.handle.net/10230/27837
• dc.language.iso engca
• dc.publisher International Speech Communication Associationca
• dc.relation.ispartof Barnes J, Brugos A, Shattuck-Hufnagel S, Veilleux N, editors. Speech Prosody 2016; 2016 May 31-June 3; Boston (MA, USA). [place unknown]: International Speech Communication Association; 2016. p. 1143-7.
• dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/645012ca
• dc.rights © ISCAca
• dc.rights.accessRights info:eu-repo/semantics/openAccessca
• dc.subject.keyword Discourse uniten
• dc.subject.keyword Prosodic cueen
• dc.subject.keyword Paragraph boundaryen
• dc.subject.keyword Speech synthesisen
• dc.title Paragraph-based prosodic cues for speech synthesis applicationsca
• dc.type info:eu-repo/semantics/conferenceObjectca
• dc.type.version info:eu-repo/semantics/publishedVersionca