Presentation 2011/12/12
Predicting Phrase Boundary Tone Labels from Text for Expressive Text-to-Speech Synthesis
HIDEHARU NAKAJIMA, HIDEYUKI MIZUNO, OSAMU YOSHIOKA, SATOSHI TAKAHASHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes the statistical method for predicting, from the input text, phrase boundary tone labels which shows more varieties in expressive speech than in reading speech. This method uses both lexical information and phrase boundary locations obtained by the language analyzer in conventional reading style text-to-speech synthesizers. Accordingly, obtained models reflect both domain and speaker specific speaking styles. Through the experiments, we confirmed that our model uses simple and a few features to achieve the same or higher correlation coefficients with correct answer labels (Cohen's kappa) than the conventional classification tree based method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English)
Paper # Vol.2011-SLP-89 No.29
Date of Issue

Conference Information
Committee NLC
Conference Date 2011/12/12(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 Natural Language Understanding and Models of Communication (NLC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Predicting Phrase Boundary Tone Labels from Text for Expressive Text-to-Speech Synthesis
Sub Title (in English)
Keyword(1)
1st Author's Name HIDEHARU NAKAJIMA
1st Author's Affiliation NTT Cyber Space Laboratories, NTT Corporation()
2nd Author's Name HIDEYUKI MIZUNO
2nd Author's Affiliation NTT Cyber Space Laboratories, NTT Corporation
3rd Author's Name OSAMU YOSHIOKA
3rd Author's Affiliation NTT Cyber Space Laboratories, NTT Corporation
4th Author's Name SATOSHI TAKAHASHI
4th Author's Affiliation NTT Cyber Space Laboratories, NTT Corporation
Date 2011/12/12
Paper # Vol.2011-SLP-89 No.29
Volume (vol) vol.111
Number (no) 364
Page pp.pp.-
#Pages 6
Date of Issue