SPEECH SYNTHESIS BY RULE USING AN OPTIMAL SELECTION OF NON-UNIFORM SYNTHESIS UNITS.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

68 Citations (Scopus)

Abstract

A synthesis scheme is proposed for the optimal selection and extraction of synthesis units. This synthesis scheme has two advantages in the usage of speech segment units. One is the flexible use of nonuniform synthesis units and the other is the optimal choice of a unit sequence for an input phoneme string using appropriateness measures. In this synthesis system, all phoneme subsequences in each synthesis unit are also used as synthesis units. To facilitate the search for appropriate unit candidates, a phoneme sequence entry dictionary is constrictive for a given speech set. Statistical analysis results are presented for Japanese phoneme sequences based on distributions in a word dictionary and a body of text. This investigation provides an estimate of the appropriate number of Japanese phoneme sequences in this synthesis scheme.

Original languageEnglish
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
PublisherIEEE
Pages679-682
Number of pages4
Publication statusPublished - 1988
Externally publishedYes

Fingerprint

Speech synthesis
phonemes
synthesis
dictionaries
Glossaries
entry
statistical analysis
Statistical methods
strings
estimates

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Acoustics and Ultrasonics

Cite this

Sagisaka, Y. (1988). SPEECH SYNTHESIS BY RULE USING AN OPTIMAL SELECTION OF NON-UNIFORM SYNTHESIS UNITS. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 679-682). IEEE.

SPEECH SYNTHESIS BY RULE USING AN OPTIMAL SELECTION OF NON-UNIFORM SYNTHESIS UNITS. / Sagisaka, Yoshinori.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. IEEE, 1988. p. 679-682.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sagisaka, Y 1988, SPEECH SYNTHESIS BY RULE USING AN OPTIMAL SELECTION OF NON-UNIFORM SYNTHESIS UNITS. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. IEEE, pp. 679-682.
Sagisaka Y. SPEECH SYNTHESIS BY RULE USING AN OPTIMAL SELECTION OF NON-UNIFORM SYNTHESIS UNITS. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. IEEE. 1988. p. 679-682
Sagisaka, Yoshinori. / SPEECH SYNTHESIS BY RULE USING AN OPTIMAL SELECTION OF NON-UNIFORM SYNTHESIS UNITS. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. IEEE, 1988. pp. 679-682
@inproceedings{492734b9211b48b88e19e57d1985efe2,
title = "SPEECH SYNTHESIS BY RULE USING AN OPTIMAL SELECTION OF NON-UNIFORM SYNTHESIS UNITS.",
abstract = "A synthesis scheme is proposed for the optimal selection and extraction of synthesis units. This synthesis scheme has two advantages in the usage of speech segment units. One is the flexible use of nonuniform synthesis units and the other is the optimal choice of a unit sequence for an input phoneme string using appropriateness measures. In this synthesis system, all phoneme subsequences in each synthesis unit are also used as synthesis units. To facilitate the search for appropriate unit candidates, a phoneme sequence entry dictionary is constrictive for a given speech set. Statistical analysis results are presented for Japanese phoneme sequences based on distributions in a word dictionary and a body of text. This investigation provides an estimate of the appropriate number of Japanese phoneme sequences in this synthesis scheme.",
author = "Yoshinori Sagisaka",
year = "1988",
language = "English",
pages = "679--682",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - SPEECH SYNTHESIS BY RULE USING AN OPTIMAL SELECTION OF NON-UNIFORM SYNTHESIS UNITS.

AU - Sagisaka, Yoshinori

PY - 1988

Y1 - 1988

N2 - A synthesis scheme is proposed for the optimal selection and extraction of synthesis units. This synthesis scheme has two advantages in the usage of speech segment units. One is the flexible use of nonuniform synthesis units and the other is the optimal choice of a unit sequence for an input phoneme string using appropriateness measures. In this synthesis system, all phoneme subsequences in each synthesis unit are also used as synthesis units. To facilitate the search for appropriate unit candidates, a phoneme sequence entry dictionary is constrictive for a given speech set. Statistical analysis results are presented for Japanese phoneme sequences based on distributions in a word dictionary and a body of text. This investigation provides an estimate of the appropriate number of Japanese phoneme sequences in this synthesis scheme.

AB - A synthesis scheme is proposed for the optimal selection and extraction of synthesis units. This synthesis scheme has two advantages in the usage of speech segment units. One is the flexible use of nonuniform synthesis units and the other is the optimal choice of a unit sequence for an input phoneme string using appropriateness measures. In this synthesis system, all phoneme subsequences in each synthesis unit are also used as synthesis units. To facilitate the search for appropriate unit candidates, a phoneme sequence entry dictionary is constrictive for a given speech set. Statistical analysis results are presented for Japanese phoneme sequences based on distributions in a word dictionary and a body of text. This investigation provides an estimate of the appropriate number of Japanese phoneme sequences in this synthesis scheme.

UR - http://www.scopus.com/inward/record.url?scp=0023756465&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0023756465&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0023756465

SP - 679

EP - 682

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

PB - IEEE

ER -