Presentation 2003/8/15
Optimizing Sub-Cost Functions for Segment Selection Based on Perceptual Evaluations in Concatenative Speech Synthesis
Tomoki TODA, Hisashi KAWAI, Minoru TSUZAKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In concatenative speech synthesis, the naturalness of synthetic speech is affected by various factors. A cost for segment selection is calculated by integrating some sub-costs capturing the degradation of naturalness caused by such factors. In this paper, we optimize each sub-cost function for converting a feature into a sub-cost based on perceptual evaluations. Test sets for evaluating sub-costs are constructed by controlling variations of sub-costs to focus on each sub-cost to be evaluated. We clarify the effectiveness of optimizing sub-cost functions based on perceptual evaluations from a result of a preference test comparing synthetic speech before optimizing sub-cost functions with that after optimizing sub-cost functions.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Concatenative speech synthesis / Segment selection / Sub-cost functions / Perceptual evaluations / Degradation of naturalness
Paper # SP2003-81
Date of Issue

Conference Information
Committee SP
Conference Date 2003/8/15(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Optimizing Sub-Cost Functions for Segment Selection Based on Perceptual Evaluations in Concatenative Speech Synthesis
Sub Title (in English)
Keyword(1) Concatenative speech synthesis
Keyword(2) Segment selection
Keyword(3) Sub-cost functions
Keyword(4) Perceptual evaluations
Keyword(5) Degradation of naturalness
1st Author's Name Tomoki TODA
1st Author's Affiliation ATR Spoken Language Translation Research Laboratories()
2nd Author's Name Hisashi KAWAI
2nd Author's Affiliation ATR Spoken Language Translation Research Laboratories
3rd Author's Name Minoru TSUZAKI
3rd Author's Affiliation ATR Spoken Language Translation Research Laboratories
Date 2003/8/15
Paper # SP2003-81
Volume (vol) vol.103
Number (no) 264
Page pp.pp.-
#Pages 6
Date of Issue