Nature Identical Prosody

OPEN ARCHIVE

Union Jack
Dannebrog

Nature Identical Prosody

Vis færre oplysninger

dc.contributor.author Juel Henrichsen, Peter
dc.date.accessioned 2012-12-12
dc.date.accessioned 2012-12-10T09:50:13Z
dc.date.available 2012-12-10T09:50:13Z
dc.date.issued 2012-12-12
dc.identifier.uri http://hdl.handle.net/10398/8595
dc.description.abstract Today's synthetic voices are largely based on diphone synthesis (DiSyn) and unit selection synthesis (UnitSyn). In most DiSyn systems, prosodic envelopes are generated with formal models while UnitSyn systems refer to extensive, highly indexed sound databases. Each approach has its drawbacks; such as low naturalness (DiSyn) and dependence on huge amounts of background data (UnitSyn). We present a hybrid model based on high-level speech data. As preliminary tests show, prosodic models combining DiSyn style at the phone level with UnitSyn style at the supra-segmental levels may approach UnitSyn quality on a DiSyn footprint. Our test data are Danish, but our algorithm is language neutral. en_US
dc.format.extent 2 en_US
dc.language eng en_US
dc.title Nature Identical Prosody en_US
dc.type cp en_US
dc.accessionstatus modt12dec12 lbjl en_US
dc.contributor.corporation Copenhagen Business School. CBS en_US
dc.contributor.department Department of International Business Communication and Politics en_US
dc.contributor.departmentshort IBC en_US
dc.contributor.departmentuk Department of International Business Communication and Politics en_US
dc.contributor.departmentukshort IBC en_US
dc.description.notes Paper presented at Swedish Language Technology Conference SLTC 2012, Lund, Sweden, October 24-26, 2012 en_US
dc.publisher.city Frederiksberg en_US
dc.publisher.year 2 en_US
dc.title.subtitle Data-driven prosodic feature assignment for diphone synthesis en_US


Creative Commons License This work is licensed under a Creative Commons License.

Filer Størrelse Format Vis
Henrichsen.pdf 154.5Kb PDF Vis/Åbn Conference paper

Dette dokument findes i følgende samling(er)

Vis færre oplysninger