Presentation 1995/5/19
Learning of Time Variant Patterns of LSP parameters using Neural Networks for Speech Synthesis
Tadaaki Shimizu, Yoshihiko Shindo, Naoki Isu, Kazuhiro Sugata,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In the conventional rule-based speech synthesis methods, synthesized speech is composed from CVC or VCV syllabic concatenation units. These methods require a large number of concatenation units. We proposed a speech synthesis method based on concatenation of phone segments using neural networks. Here, neural network memorizes the time patterns in the form of data compression. This paper presents a simplified experiment with synthesizing speech that is made from vowels. In this case, the neural network generate time variant patterns of LSP parameters of glide in speech.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) speech synthesis by rule / LSP parameter / Neural Network / glide
Paper #
Date of Issue

Conference Information
Committee NLP
Conference Date 1995/5/19(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 Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Learning of Time Variant Patterns of LSP parameters using Neural Networks for Speech Synthesis
Sub Title (in English)
Keyword(1) speech synthesis by rule
Keyword(2) LSP parameter
Keyword(3) Neural Network
Keyword(4) glide
1st Author's Name Tadaaki Shimizu
1st Author's Affiliation Department of Information and Knowledge Engineering, Tottori University()
2nd Author's Name Yoshihiko Shindo
2nd Author's Affiliation Department of Information and Knowledge Engineering, Tottori University
3rd Author's Name Naoki Isu
3rd Author's Affiliation Department of Information and Knowledge Engineering, Tottori University
4th Author's Name Kazuhiro Sugata
4th Author's Affiliation Department of Information and Knowledge Engineering, Tottori University
Date 1995/5/19
Paper #
Volume (vol) vol.95
Number (no) 47
Page pp.pp.-
#Pages 8
Date of Issue