Nature Identical Prosody

OPEN ARCHIVE

Union Jack
Dannebrog

Nature Identical Prosody

Show full item record

Title: Nature Identical Prosody
Data-driven prosodic feature assignment for diphone synthesis
Author: Juel Henrichsen, Peter
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.
URI: http://hdl.handle.net/10398/8595
Date: 2012-12-12
Notes: Paper presented at Swedish Language Technology Conference SLTC 2012, Lund, Sweden, October 24-26, 2012

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

Files Size Format View
Henrichsen.pdf 154.5Kb PDF View/Open Conference paper

This item appears in the following Collection(s)

Show full item record