An automatic broadcast system for a weather report radio program

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

Research output: Contribution to journalArticle

Abstract

Here we describe a speech-synthesis method using templates that can generate recording-sentence sets for speech databases and produce natural sounding synthesized speech. Applying this method to the Japan Broadcasting Corporation (NHK) weather report radio program reduced the size of the recording-sentence set required to just a fraction of that needed by a comparable method. After integrating the recording voice of the generated recording-sentence set into the speech database, speech was produced by a voice synthesizer using templates. In a paired-comparison test, 66% of the speech samples synthesized by our system using templates were preferred to those produced by a conventional voice synthesizer. In an evaluation test using a five-point mean opinion score (MOS) scale, the speech samples synthesized by our system scored 4.97, whereas the maximum score for commercially available voice synthesizers was 3.09. In addition, we developed an automatic broadcast system for the weather report program using the speech-synthesis method and speech-rate converter. The system was evaluated using real weather data for more than 1 year, and exhibited sufficient stability and synthesized speech quality for broadcast purposes.

Original languageEnglish
Article number6572852
Pages (from-to)548-555
Number of pages8
JournalIEEE Transactions on Broadcasting
Volume59
Issue number3
DOIs
Publication statusPublished - 2013

Fingerprint

Speech synthesis
Broadcasting
Industry

Keywords

  • Recording-sentence set
  • speech-rate conversion
  • templates
  • voice synthesizer

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Media Technology

Cite this

Segi, H., Takou, R., Seiyama, N., Takagi, T., Uematsu, Y., Saito, H., & Ozawa, S. (2013). An automatic broadcast system for a weather report radio program. IEEE Transactions on Broadcasting, 59(3), 548-555. [6572852]. https://doi.org/10.1109/TBC.2013.2272406

An automatic broadcast system for a weather report radio program. / Segi, Hiroyuki; Takou, Reiko; Seiyama, Nobumasa; Takagi, Tohru; Uematsu, Yuko; Saito, Hideo; Ozawa, Shinji.

In: IEEE Transactions on Broadcasting, Vol. 59, No. 3, 6572852, 2013, p. 548-555.

Research output: Contribution to journalArticle

Segi, H, Takou, R, Seiyama, N, Takagi, T, Uematsu, Y, Saito, H & Ozawa, S 2013, 'An automatic broadcast system for a weather report radio program', IEEE Transactions on Broadcasting, vol. 59, no. 3, 6572852, pp. 548-555. https://doi.org/10.1109/TBC.2013.2272406
Segi, Hiroyuki ; Takou, Reiko ; Seiyama, Nobumasa ; Takagi, Tohru ; Uematsu, Yuko ; Saito, Hideo ; Ozawa, Shinji. / An automatic broadcast system for a weather report radio program. In: IEEE Transactions on Broadcasting. 2013 ; Vol. 59, No. 3. pp. 548-555.
@article{7645148daccb465aa0c58bf0bafb2cde,
title = "An automatic broadcast system for a weather report radio program",
abstract = "Here we describe a speech-synthesis method using templates that can generate recording-sentence sets for speech databases and produce natural sounding synthesized speech. Applying this method to the Japan Broadcasting Corporation (NHK) weather report radio program reduced the size of the recording-sentence set required to just a fraction of that needed by a comparable method. After integrating the recording voice of the generated recording-sentence set into the speech database, speech was produced by a voice synthesizer using templates. In a paired-comparison test, 66{\%} of the speech samples synthesized by our system using templates were preferred to those produced by a conventional voice synthesizer. In an evaluation test using a five-point mean opinion score (MOS) scale, the speech samples synthesized by our system scored 4.97, whereas the maximum score for commercially available voice synthesizers was 3.09. In addition, we developed an automatic broadcast system for the weather report program using the speech-synthesis method and speech-rate converter. The system was evaluated using real weather data for more than 1 year, and exhibited sufficient stability and synthesized speech quality for broadcast purposes.",
keywords = "Recording-sentence set, speech-rate conversion, templates, voice synthesizer",
author = "Hiroyuki Segi and Reiko Takou and Nobumasa Seiyama and Tohru Takagi and Yuko Uematsu and Hideo Saito and Shinji Ozawa",
year = "2013",
doi = "10.1109/TBC.2013.2272406",
language = "English",
volume = "59",
pages = "548--555",
journal = "IEEE Transactions on Broadcasting",
issn = "0018-9316",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - An automatic broadcast system for a weather report radio program

AU - Segi, Hiroyuki

AU - Takou, Reiko

AU - Seiyama, Nobumasa

AU - Takagi, Tohru

AU - Uematsu, Yuko

AU - Saito, Hideo

AU - Ozawa, Shinji

PY - 2013

Y1 - 2013

N2 - Here we describe a speech-synthesis method using templates that can generate recording-sentence sets for speech databases and produce natural sounding synthesized speech. Applying this method to the Japan Broadcasting Corporation (NHK) weather report radio program reduced the size of the recording-sentence set required to just a fraction of that needed by a comparable method. After integrating the recording voice of the generated recording-sentence set into the speech database, speech was produced by a voice synthesizer using templates. In a paired-comparison test, 66% of the speech samples synthesized by our system using templates were preferred to those produced by a conventional voice synthesizer. In an evaluation test using a five-point mean opinion score (MOS) scale, the speech samples synthesized by our system scored 4.97, whereas the maximum score for commercially available voice synthesizers was 3.09. In addition, we developed an automatic broadcast system for the weather report program using the speech-synthesis method and speech-rate converter. The system was evaluated using real weather data for more than 1 year, and exhibited sufficient stability and synthesized speech quality for broadcast purposes.

AB - Here we describe a speech-synthesis method using templates that can generate recording-sentence sets for speech databases and produce natural sounding synthesized speech. Applying this method to the Japan Broadcasting Corporation (NHK) weather report radio program reduced the size of the recording-sentence set required to just a fraction of that needed by a comparable method. After integrating the recording voice of the generated recording-sentence set into the speech database, speech was produced by a voice synthesizer using templates. In a paired-comparison test, 66% of the speech samples synthesized by our system using templates were preferred to those produced by a conventional voice synthesizer. In an evaluation test using a five-point mean opinion score (MOS) scale, the speech samples synthesized by our system scored 4.97, whereas the maximum score for commercially available voice synthesizers was 3.09. In addition, we developed an automatic broadcast system for the weather report program using the speech-synthesis method and speech-rate converter. The system was evaluated using real weather data for more than 1 year, and exhibited sufficient stability and synthesized speech quality for broadcast purposes.

KW - Recording-sentence set

KW - speech-rate conversion

KW - templates

KW - voice synthesizer

UR - http://www.scopus.com/inward/record.url?scp=84883463897&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883463897&partnerID=8YFLogxK

U2 - 10.1109/TBC.2013.2272406

DO - 10.1109/TBC.2013.2272406

M3 - Article

AN - SCOPUS:84883463897

VL - 59

SP - 548

EP - 555

JO - IEEE Transactions on Broadcasting

JF - IEEE Transactions on Broadcasting

SN - 0018-9316

IS - 3

M1 - 6572852

ER -