DSpace Repository

A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis

Show simple item record

dc.contributor.author Tomoki Toda en
dc.contributor.author Keiichi Tokuda en
dc.date.accessioned 2012-07-05T07:00:48Z en
dc.date.available 2012-07-05T07:00:48Z en
dc.date.issued 2007-05 en
dc.identifier.issn 0916-8532 en
dc.identifier.uri http://hdl.handle.net/10061/7825 en
dc.description.abstract This paper describes a novel parameter generation algorithm for an HMM-based speech synthesis technique. The conventional algorithm generates a parameter trajectory of static features that maximizes the likelihood of a given HMM for the parameter sequence consisting of the static and dynamic features under an explicit constraint between those two features. The generated trajectory is often excessively smoothed due to the statistical processing. Using the over-smoothed speech parameters usually causes muffled sounds. In order to alleviate the over-smoothing effect, we propose a generation algorithm considering not only the HMM likelihood maximized in the conventional algorithm but also a likelihood for a global variance (GV) of the generated trajectory. The latter likelihood works as a penalty for the over-smoothing, i.e., a reduction of the GV of the generated trajectory. The result of a perceptual evaluation demonstrates that the proposed algorithm causes considerably large improvements in the naturalness of synthetic speech. en
dc.language.iso en en
dc.publisher 電子情報通信学会 ja
dc.rights Copyright (C) 2007 電子情報通信学会. ja
dc.subject HMM-based speech synthesis en
dc.subject speech parameter generation en
dc.subject maximum likelihood criterion en
dc.subject over-smoothing effect en
dc.subject global variance en
dc.title A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis en
dc.type.nii Journal Article en
dc.textversion publisher en
dc.identifier.ncid AA10826272 en
dc.identifier.jtitle IEICE Transactions on Information and Systems en
dc.identifier.volume E90-D en
dc.identifier.issue 5 en
dc.identifier.spage 816 en
dc.identifier.epage 824 en
dc.relation.doi 10.1093/ietisy/e90-d.5.816 en
dc.identifier.NAIST-ID 73292716 en

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace

Advanced Search


My Account