Presentation | 2007/10/18 Corpus-based generation of prosodic features from text using generation process model of fundamental frequency contours Keiko OCHI, Keikichi HIROSE, Nobuaki MINEMATSU, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The paper presents a corpus-based method for generating prosodic features from a given text. The method consists of three steps : First, position and duration of pauses are predicted using linguistic information extracted from the text. Then, phone durations are predicted, and finally F0 contour generation process model (F0 model) parameters (command timings and amplitudes) are predicted. Information predicted in preceding steps is used for the following steps, thus obtaining the consistency between predicted prosodic features. By adding constraints on the accent command timings as a post processing, a better quality was realized in synthetic speech when predicted prosodic features were used. Validity of the developed method was confirmed through a listening test of synthetic speech. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Fundamental frequency contour generation process model / prosody / text to speech synthesis |
Paper # | SP2007-78 |
Date of Issue |
Conference Information | |
Committee | SP |
---|---|
Conference Date | 2007/10/18(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) | Corpus-based generation of prosodic features from text using generation process model of fundamental frequency contours |
Sub Title (in English) | |
Keyword(1) | Fundamental frequency contour generation process model |
Keyword(2) | prosody |
Keyword(3) | text to speech synthesis |
1st Author's Name | Keiko OCHI |
1st Author's Affiliation | Department of Information and Communication Engineering, School of Information Science and Technology, University of Tokyo() |
2nd Author's Name | Keikichi HIROSE |
2nd Author's Affiliation | Department of Information and Communication Engineering, School of Information Science and Technology, University of Tokyo |
3rd Author's Name | Nobuaki MINEMATSU |
3rd Author's Affiliation | Dept. of Frontier Informatics, School of Frontier Sciences, University of Tokyo |
Date | 2007/10/18 |
Paper # | SP2007-78 |
Volume (vol) | vol.107 |
Number (no) | 282 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |