Welcome to the UPF Digital Repository

Paragraph-based prosodic cues for speech synthesis applications

Show simple item record

dc.contributor.author Farrús, Mireia
dc.contributor.author Lai, Catherine
dc.contributor.author Moore, Johanna D.
dc.date.accessioned 2016-12-22T18:46:33Z
dc.date.available 2016-12-22T18:46:33Z
dc.date.issued 2016
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.2016-235
dc.identifier.issn 2333-2042
dc.identifier.uri http://hdl.handle.net/10230/27837
dc.description Paper presented at: Speech Prosody 2016; 2016 May 31-June 3; Boston (MA, USA)
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.
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 grant
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher International Speech Communication Association
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.rights © ISCA
dc.title Paragraph-based prosodic cues for speech synthesis applications
dc.type info:eu-repo/semantics/conferenceObject
dc.identifier.doi http://dx.doi.org/10.21437/SpeechProsody.2016-235
dc.subject.keyword Discourse unit
dc.subject.keyword Prosodic cue
dc.subject.keyword Paragraph boundary
dc.subject.keyword Speech synthesis
dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/645012
dc.rights.accessRights info:eu-repo/semantics/openAccess
dc.type.version info:eu-repo/semantics/publishedVersion

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account

Statistics

In collaboration with Compliant to Partaking