File Download
Supplementary

Conference Paper: Modelling Japanese intonation using PENTAtrainer2

TitleModelling Japanese intonation using PENTAtrainer2
Authors
KeywordsFocus
Japanese
Sentence type
Issue Date2015
Citation
The 18th International Congress of Phonetic Scences (ICPhS 2015), Glasgow, UK., 10-14 August 2015. In Conference Proceedings, 2015, p. 86 How to Cite?
AbstractThis paper presents results from Japanese intonation modelling using PENTAtrainer2, an articulatory synthesiser. Our first aim is to show that PENTA, on which PENTAtrainer2 is based, can achieve high accuracy in predictive synthesis of varying intonation contours. We trained the synthesiser on a 6251-sentence functionally annotated corpus and generated F0 contours for each communicative condition. The accuracy of speaker-dependent and independent synthesis, together with naturalness ratings, show that PENTA is effective in modelling Japanese intonation. This suggests that once contextual variability is incorporated into a model, multi-functional targets alone would suffice as the prosodic representation even in a sizeable corpus.
Persistent Identifierhttp://hdl.handle.net/10722/220082

 

DC FieldValueLanguage
dc.contributor.authorLee, A-
dc.contributor.authorXu, Y-
dc.date.accessioned2015-10-16T06:28:40Z-
dc.date.available2015-10-16T06:28:40Z-
dc.date.issued2015-
dc.identifier.citationThe 18th International Congress of Phonetic Scences (ICPhS 2015), Glasgow, UK., 10-14 August 2015. In Conference Proceedings, 2015, p. 86-
dc.identifier.urihttp://hdl.handle.net/10722/220082-
dc.description.abstractThis paper presents results from Japanese intonation modelling using PENTAtrainer2, an articulatory synthesiser. Our first aim is to show that PENTA, on which PENTAtrainer2 is based, can achieve high accuracy in predictive synthesis of varying intonation contours. We trained the synthesiser on a 6251-sentence functionally annotated corpus and generated F0 contours for each communicative condition. The accuracy of speaker-dependent and independent synthesis, together with naturalness ratings, show that PENTA is effective in modelling Japanese intonation. This suggests that once contextual variability is incorporated into a model, multi-functional targets alone would suffice as the prosodic representation even in a sizeable corpus.-
dc.languageeng-
dc.relation.ispartofProceedings of the 18th International Congress of Phonetic Sciences, ICPhS 2015-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.subjectFocus-
dc.subjectJapanese-
dc.subjectSentence type-
dc.titleModelling Japanese intonation using PENTAtrainer2-
dc.typeConference_Paper-
dc.identifier.emailLee, A: albertlee@hku.hk-
dc.identifier.authorityLee, A=rp02091-
dc.description.naturepostprint-
dc.identifier.hkuros255667-
dc.identifier.spage86-
dc.identifier.epage86-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats