WORD IDENTIFICATION METHOD FOR JAPANESE TEXT-TO-SPEECH CONVERSION SYSTEM.

Yoshinori Sagisaka, Hirokazu Sato

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

2 Citations (Scopus)

Abstract

A word identification method is proposed for Japanese text-to-speech conversion. The number of identification trials is reduced by restricting the identification to short intervals using a dynamic programming technique. Plausibility evaluation that reflects several Japanese text writing characteristics is introduced. Results show the usefulness of this identification method as well as the necessity of dictionary enrichment and of advanced intensive analyses. These advanced analyses are not only required in word identification itself but in the further text analyses needed for the generation of phonetic and prosodic information.

Original languageEnglish
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
PublisherIEEE
Pages2411-2414
Number of pages4
Publication statusPublished - 1986
Externally publishedYes

Fingerprint

Speech analysis
Glossaries
Dynamic programming
dynamic programming
dictionaries
phonetics
intervals
evaluation

ASJC Scopus subject areas

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

Cite this

Sagisaka, Y., & Sato, H. (1986). WORD IDENTIFICATION METHOD FOR JAPANESE TEXT-TO-SPEECH CONVERSION SYSTEM. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 2411-2414). IEEE.

WORD IDENTIFICATION METHOD FOR JAPANESE TEXT-TO-SPEECH CONVERSION SYSTEM. / Sagisaka, Yoshinori; Sato, Hirokazu.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. IEEE, 1986. p. 2411-2414.

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

Sagisaka, Y & Sato, H 1986, WORD IDENTIFICATION METHOD FOR JAPANESE TEXT-TO-SPEECH CONVERSION SYSTEM. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. IEEE, pp. 2411-2414.
Sagisaka Y, Sato H. WORD IDENTIFICATION METHOD FOR JAPANESE TEXT-TO-SPEECH CONVERSION SYSTEM. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. IEEE. 1986. p. 2411-2414
Sagisaka, Yoshinori ; Sato, Hirokazu. / WORD IDENTIFICATION METHOD FOR JAPANESE TEXT-TO-SPEECH CONVERSION SYSTEM. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. IEEE, 1986. pp. 2411-2414
@inproceedings{c2816812cf604f3a99a380ea2e44cf8f,
title = "WORD IDENTIFICATION METHOD FOR JAPANESE TEXT-TO-SPEECH CONVERSION SYSTEM.",
abstract = "A word identification method is proposed for Japanese text-to-speech conversion. The number of identification trials is reduced by restricting the identification to short intervals using a dynamic programming technique. Plausibility evaluation that reflects several Japanese text writing characteristics is introduced. Results show the usefulness of this identification method as well as the necessity of dictionary enrichment and of advanced intensive analyses. These advanced analyses are not only required in word identification itself but in the further text analyses needed for the generation of phonetic and prosodic information.",
author = "Yoshinori Sagisaka and Hirokazu Sato",
year = "1986",
language = "English",
pages = "2411--2414",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - WORD IDENTIFICATION METHOD FOR JAPANESE TEXT-TO-SPEECH CONVERSION SYSTEM.

AU - Sagisaka, Yoshinori

AU - Sato, Hirokazu

PY - 1986

Y1 - 1986

N2 - A word identification method is proposed for Japanese text-to-speech conversion. The number of identification trials is reduced by restricting the identification to short intervals using a dynamic programming technique. Plausibility evaluation that reflects several Japanese text writing characteristics is introduced. Results show the usefulness of this identification method as well as the necessity of dictionary enrichment and of advanced intensive analyses. These advanced analyses are not only required in word identification itself but in the further text analyses needed for the generation of phonetic and prosodic information.

AB - A word identification method is proposed for Japanese text-to-speech conversion. The number of identification trials is reduced by restricting the identification to short intervals using a dynamic programming technique. Plausibility evaluation that reflects several Japanese text writing characteristics is introduced. Results show the usefulness of this identification method as well as the necessity of dictionary enrichment and of advanced intensive analyses. These advanced analyses are not only required in word identification itself but in the further text analyses needed for the generation of phonetic and prosodic information.

UR - http://www.scopus.com/inward/record.url?scp=0022920135&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0022920135&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0022920135

SP - 2411

EP - 2414

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

PB - IEEE

ER -