A database design for a concatenative speech synthesis system for the disabled

Akemi Iida; Nick Campbell

A database design for a concatenative speech synthesis system for the disabled

Akemi Iida, Nick Campbell

Research output: Contribution to conference › Paper › peer-review

Abstract

This paper reports on our research on designing a speech corpora in Japanese for a concatenative speech synthesis system that is to be used for a specific purpose. For this work, the purpose was set to assist communication for non-vocal people. Four kinds of source database for synthesis were developed by combining different speech corpora created from read speech of an Amyotropic Lateral Sclerosis (ALS) patient who was anticipating the imminent loss of his voice. This work confirmed that the recording of a minimum set of phonetically balanced sentences (129 sentences) was insufficient for concatenative speech synthesis and that a combination of these and a recording of well-read continuous-text material produced more natural sounding synthesized speech. A communication aid was developed using a concatenated speech synthesis with the database created in this work.

Original language	English
Publication status	Published - 2001
Externally published	Yes
Event	4th ISCA Tutorial and Research Workshop on Speech Synthesis, SSW 2001 - Perthshire, United Kingdom Duration: 2001 Aug 29 → 2001 Sept 1

Conference

Conference	4th ISCA Tutorial and Research Workshop on Speech Synthesis, SSW 2001
Country/Territory	United Kingdom
City	Perthshire
Period	01/8/29 → 01/9/1

ASJC Scopus subject areas

Language and Linguistics
Cultural Studies

Cite this

@conference{6ea4fe663b9046ca84382b12817c8d93,

title = "A database design for a concatenative speech synthesis system for the disabled",

abstract = "This paper reports on our research on designing a speech corpora in Japanese for a concatenative speech synthesis system that is to be used for a specific purpose. For this work, the purpose was set to assist communication for non-vocal people. Four kinds of source database for synthesis were developed by combining different speech corpora created from read speech of an Amyotropic Lateral Sclerosis (ALS) patient who was anticipating the imminent loss of his voice. This work confirmed that the recording of a minimum set of phonetically balanced sentences (129 sentences) was insufficient for concatenative speech synthesis and that a combination of these and a recording of well-read continuous-text material produced more natural sounding synthesized speech. A communication aid was developed using a concatenated speech synthesis with the database created in this work.",

author = "Akemi Iida and Nick Campbell",

note = "Funding Information: The authors would like to express their sincere appreciation to Mr. Shinnichi Yamaguchi of Fukuoka-pref., Japan. The authors also would like to thank Prof. Kimitoshi Fukudome, Kyushuu Institute of Design, Prof. Satoshi Imaizumi and Prof. Keikichi Hirose of University of Tokyo, Mr. Eiji Mitsuya and Mr. Masahiro Nishimura of ATR for their kind cooperation. Publisher Copyright: {\textcopyright} SSW 2001. All rights reserved.; 4th ISCA Tutorial and Research Workshop on Speech Synthesis, SSW 2001 ; Conference date: 29-08-2001 Through 01-09-2001",

year = "2001",

language = "English",

}

TY - CONF

T1 - A database design for a concatenative speech synthesis system for the disabled

AU - Iida, Akemi

AU - Campbell, Nick

N1 - Funding Information: The authors would like to express their sincere appreciation to Mr. Shinnichi Yamaguchi of Fukuoka-pref., Japan. The authors also would like to thank Prof. Kimitoshi Fukudome, Kyushuu Institute of Design, Prof. Satoshi Imaizumi and Prof. Keikichi Hirose of University of Tokyo, Mr. Eiji Mitsuya and Mr. Masahiro Nishimura of ATR for their kind cooperation. Publisher Copyright: © SSW 2001. All rights reserved.

PY - 2001

Y1 - 2001

N2 - This paper reports on our research on designing a speech corpora in Japanese for a concatenative speech synthesis system that is to be used for a specific purpose. For this work, the purpose was set to assist communication for non-vocal people. Four kinds of source database for synthesis were developed by combining different speech corpora created from read speech of an Amyotropic Lateral Sclerosis (ALS) patient who was anticipating the imminent loss of his voice. This work confirmed that the recording of a minimum set of phonetically balanced sentences (129 sentences) was insufficient for concatenative speech synthesis and that a combination of these and a recording of well-read continuous-text material produced more natural sounding synthesized speech. A communication aid was developed using a concatenated speech synthesis with the database created in this work.

AB - This paper reports on our research on designing a speech corpora in Japanese for a concatenative speech synthesis system that is to be used for a specific purpose. For this work, the purpose was set to assist communication for non-vocal people. Four kinds of source database for synthesis were developed by combining different speech corpora created from read speech of an Amyotropic Lateral Sclerosis (ALS) patient who was anticipating the imminent loss of his voice. This work confirmed that the recording of a minimum set of phonetically balanced sentences (129 sentences) was insufficient for concatenative speech synthesis and that a combination of these and a recording of well-read continuous-text material produced more natural sounding synthesized speech. A communication aid was developed using a concatenated speech synthesis with the database created in this work.

UR - http://www.scopus.com/inward/record.url?scp=85132576123&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85132576123&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85132576123

T2 - 4th ISCA Tutorial and Research Workshop on Speech Synthesis, SSW 2001

Y2 - 29 August 2001 through 1 September 2001

ER -

A database design for a concatenative speech synthesis system for the disabled

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this