Edinburgh Research Archive

Modelling Pitch Accent Types for Polish Speech Synthesis

dc.contributor.author
Oliver, Dominika
en
dc.contributor.author
Clark, Robert A J
en
dc.date.accessioned
2006-05-12T13:15:05Z
dc.date.available
2006-05-12T13:15:05Z
dc.date.issued
2005
dc.description.abstract
We describe a Polish prosody modelling module for the Festival speech synthesis system. The module uses classification and regression trees for accent type prediction and a linear regression technique for F0 contour generation for these contours. The techniques used to attempt to overcome problems with the only available data are shown. We demonstrate how improvements were achieved by the use of a modified F0 stylisation, accent type clustering and language specific features. Results of a formal perception study show a significant preference for the new intonation model over the original one.
en
dc.format.extent
152484 bytes
en
dc.format.mimetype
application/pdf
en
dc.identifier.citation
In Proceedings, Interspeech'2005 - Eurospeech, 9th European Conference on Speech Communication and Technology, Lisbon, Portugal, September 4-8, 2005
dc.identifier.uri
http://hdl.handle.net/1842/1052
dc.language.iso
en
dc.subject
Festival
en
dc.subject
Polish prosody modelling
en
dc.subject
speech
en
dc.subject
speech synthesis
en
dc.title
Modelling Pitch Accent Types for Polish Speech Synthesis
en
dc.type
Conference Paper
en

Files

Original bundle

Now showing 1 - 1 of 1
Name:
oliverclark_interspeech05.pdf
Size:
148.91 KB
Format:
Adobe Portable Document Format

This item appears in the following Collection(s)