Sentence-generating system for speech synthesis using templates and application for the 'Weather Report" radio program

Hiroyuki Segi, Reiko Takou, Nobumasa Seiyamat, Tohru Takagi, Hideo Saito, Shinji Ozawat

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The design method of a sentence set for a speech-synthesis database strongly influences the quality of the synthesized speech. To minimize the costs associated with making the speech recordings and constructing the speech database, the number of the sentence set should be limited. However, if a sentence set does not include sufficient data, the quality of the synthesized speech can be inadequate. In this paper, we propose a method for generating a sentence set from templates. When applied to the templates in the "Weather Report" radio program, the proposed method reduced the number of the sentence set to less than several percent of that required by a comparison method. In addition, the mean opinion score of speech samples synthesized using the proposed method was 4.32 on a five-point scale.

Original languageEnglish
Pages (from-to)76-83
Number of pages8
JournalKyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers
Volume65
Issue number1
DOIs
Publication statusPublished - 2011

Fingerprint

Speech synthesis
Costs

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Media Technology
  • Computer Science Applications

Cite this

Sentence-generating system for speech synthesis using templates and application for the 'Weather Report" radio program. / Segi, Hiroyuki; Takou, Reiko; Seiyamat, Nobumasa; Takagi, Tohru; Saito, Hideo; Ozawat, Shinji.

In: Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers, Vol. 65, No. 1, 2011, p. 76-83.

Research output: Contribution to journalArticle

@article{5809439be6cd4d5383affc2299cdeaeb,
title = "Sentence-generating system for speech synthesis using templates and application for the 'Weather Report{"} radio program",
abstract = "The design method of a sentence set for a speech-synthesis database strongly influences the quality of the synthesized speech. To minimize the costs associated with making the speech recordings and constructing the speech database, the number of the sentence set should be limited. However, if a sentence set does not include sufficient data, the quality of the synthesized speech can be inadequate. In this paper, we propose a method for generating a sentence set from templates. When applied to the templates in the {"}Weather Report{"} radio program, the proposed method reduced the number of the sentence set to less than several percent of that required by a comparison method. In addition, the mean opinion score of speech samples synthesized using the proposed method was 4.32 on a five-point scale.",
author = "Hiroyuki Segi and Reiko Takou and Nobumasa Seiyamat and Tohru Takagi and Hideo Saito and Shinji Ozawat",
year = "2011",
doi = "10.3169/itej.65.76",
language = "English",
volume = "65",
pages = "76--83",
journal = "Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers",
issn = "1342-6907",
publisher = "Institute of Image Information and Television Engineers",
number = "1",

}

TY - JOUR

T1 - Sentence-generating system for speech synthesis using templates and application for the 'Weather Report" radio program

AU - Segi, Hiroyuki

AU - Takou, Reiko

AU - Seiyamat, Nobumasa

AU - Takagi, Tohru

AU - Saito, Hideo

AU - Ozawat, Shinji

PY - 2011

Y1 - 2011

N2 - The design method of a sentence set for a speech-synthesis database strongly influences the quality of the synthesized speech. To minimize the costs associated with making the speech recordings and constructing the speech database, the number of the sentence set should be limited. However, if a sentence set does not include sufficient data, the quality of the synthesized speech can be inadequate. In this paper, we propose a method for generating a sentence set from templates. When applied to the templates in the "Weather Report" radio program, the proposed method reduced the number of the sentence set to less than several percent of that required by a comparison method. In addition, the mean opinion score of speech samples synthesized using the proposed method was 4.32 on a five-point scale.

AB - The design method of a sentence set for a speech-synthesis database strongly influences the quality of the synthesized speech. To minimize the costs associated with making the speech recordings and constructing the speech database, the number of the sentence set should be limited. However, if a sentence set does not include sufficient data, the quality of the synthesized speech can be inadequate. In this paper, we propose a method for generating a sentence set from templates. When applied to the templates in the "Weather Report" radio program, the proposed method reduced the number of the sentence set to less than several percent of that required by a comparison method. In addition, the mean opinion score of speech samples synthesized using the proposed method was 4.32 on a five-point scale.

UR - http://www.scopus.com/inward/record.url?scp=84856837804&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856837804&partnerID=8YFLogxK

U2 - 10.3169/itej.65.76

DO - 10.3169/itej.65.76

M3 - Article

VL - 65

SP - 76

EP - 83

JO - Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers

JF - Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers

SN - 1342-6907

IS - 1

ER -