Template-based methods for sentence generation and speech synthesis

Hiroyuki Segi, Reiko Takou, Nobumasa Seiyama, Tohru Takagi, Hideo Saito, Shinji Ozawa

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

Abstract

Here we propose a sentence-generation method using templates that can be applied to create a speech database. This method requires the recording of a relatively small sentence set, and the resultant speech database can generate comparatively natural sounding synthesized speech. Applying this method to the Japan Broadcasting Corporation (NHK) weather report radio program reduced the size of the required sentence set to just a fraction of that required by comparable methods. We also propose a speech-synthesis method using templates. In an evaluation test, 66% of the speech samples synthesized by the proposed method using templates were preferred to those produced by the conventional concatenative speech-synthesis method.

Original languageEnglish
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Pages1757-1760
Number of pages4
DOIs
Publication statusPublished - 2011
Event36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Prague, Czech Republic
Duration: 2011 May 222011 May 27

Other

Other36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011
CountryCzech Republic
CityPrague
Period11/5/2211/5/27

Fingerprint

Speech synthesis
Broadcasting
Industry

Keywords

  • recording sentences
  • sentence generation
  • speech database
  • speech synthesis
  • templates

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Segi, H., Takou, R., Seiyama, N., Takagi, T., Saito, H., & Ozawa, S. (2011). Template-based methods for sentence generation and speech synthesis. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 1757-1760). [5946842] https://doi.org/10.1109/ICASSP.2011.5946842

Template-based methods for sentence generation and speech synthesis. / Segi, Hiroyuki; Takou, Reiko; Seiyama, Nobumasa; Takagi, Tohru; Saito, Hideo; Ozawa, Shinji.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2011. p. 1757-1760 5946842.

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

Segi, H, Takou, R, Seiyama, N, Takagi, T, Saito, H & Ozawa, S 2011, Template-based methods for sentence generation and speech synthesis. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings., 5946842, pp. 1757-1760, 36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011, Prague, Czech Republic, 11/5/22. https://doi.org/10.1109/ICASSP.2011.5946842
Segi H, Takou R, Seiyama N, Takagi T, Saito H, Ozawa S. Template-based methods for sentence generation and speech synthesis. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2011. p. 1757-1760. 5946842 https://doi.org/10.1109/ICASSP.2011.5946842
Segi, Hiroyuki ; Takou, Reiko ; Seiyama, Nobumasa ; Takagi, Tohru ; Saito, Hideo ; Ozawa, Shinji. / Template-based methods for sentence generation and speech synthesis. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2011. pp. 1757-1760
@inproceedings{93977a005f954e2c9efe4225c1e7fb61,
title = "Template-based methods for sentence generation and speech synthesis",
abstract = "Here we propose a sentence-generation method using templates that can be applied to create a speech database. This method requires the recording of a relatively small sentence set, and the resultant speech database can generate comparatively natural sounding synthesized speech. Applying this method to the Japan Broadcasting Corporation (NHK) weather report radio program reduced the size of the required sentence set to just a fraction of that required by comparable methods. We also propose a speech-synthesis method using templates. In an evaluation test, 66{\%} of the speech samples synthesized by the proposed method using templates were preferred to those produced by the conventional concatenative speech-synthesis method.",
keywords = "recording sentences, sentence generation, speech database, speech synthesis, templates",
author = "Hiroyuki Segi and Reiko Takou and Nobumasa Seiyama and Tohru Takagi and Hideo Saito and Shinji Ozawa",
year = "2011",
doi = "10.1109/ICASSP.2011.5946842",
language = "English",
isbn = "9781457705397",
pages = "1757--1760",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

}

TY - GEN

T1 - Template-based methods for sentence generation and speech synthesis

AU - Segi, Hiroyuki

AU - Takou, Reiko

AU - Seiyama, Nobumasa

AU - Takagi, Tohru

AU - Saito, Hideo

AU - Ozawa, Shinji

PY - 2011

Y1 - 2011

N2 - Here we propose a sentence-generation method using templates that can be applied to create a speech database. This method requires the recording of a relatively small sentence set, and the resultant speech database can generate comparatively natural sounding synthesized speech. Applying this method to the Japan Broadcasting Corporation (NHK) weather report radio program reduced the size of the required sentence set to just a fraction of that required by comparable methods. We also propose a speech-synthesis method using templates. In an evaluation test, 66% of the speech samples synthesized by the proposed method using templates were preferred to those produced by the conventional concatenative speech-synthesis method.

AB - Here we propose a sentence-generation method using templates that can be applied to create a speech database. This method requires the recording of a relatively small sentence set, and the resultant speech database can generate comparatively natural sounding synthesized speech. Applying this method to the Japan Broadcasting Corporation (NHK) weather report radio program reduced the size of the required sentence set to just a fraction of that required by comparable methods. We also propose a speech-synthesis method using templates. In an evaluation test, 66% of the speech samples synthesized by the proposed method using templates were preferred to those produced by the conventional concatenative speech-synthesis method.

KW - recording sentences

KW - sentence generation

KW - speech database

KW - speech synthesis

KW - templates

UR - http://www.scopus.com/inward/record.url?scp=80051661275&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80051661275&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2011.5946842

DO - 10.1109/ICASSP.2011.5946842

M3 - Conference contribution

AN - SCOPUS:80051661275

SN - 9781457705397

SP - 1757

EP - 1760

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

ER -