SPEAKER ADAPTATION FITTING TRAINING DATA SIZE AND CONTENTS

Masahiro Tonomura; Tetsuo Kosaka; Shoichi Matsunaga; Akito Monden

SPEAKER ADAPTATION FITTING TRAINING DATA SIZE AND CONTENTS

Masahiro Tonomura, Tetsuo Kosaka, Shoichi Matsunaga, Akito Monden

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

Abstract

This paper proposes a speaker adaptation algorithm that covers a wide range of adaptation data. The parameter smoothing technique improves adaptation performance for a small amount of adaptation data; however, this smoothing usually reduces adaptation efficiency for a large amount of adaptation data. Our method dynamically controls smoothing strength by using information on the amount of adaptation data to achieve good adaptation performance over a wide range of adaptation data. The proposed method is combined with the maximum a posteriori (MAP) estimation technique, and its effectiveness is shown on a Japanese 26 phoneme recognition test.

Original language	English
Pages	1147-1150
Number of pages	4
Publication status	Published - 1995
Externally published	Yes
Event	4th European Conference on Speech Communication and Technology, EUROSPEECH 1995 - Madrid, Spain Duration: Sep 18 1995 → Sep 21 1995

Conference

Conference	4th European Conference on Speech Communication and Technology, EUROSPEECH 1995
Country/Territory	Spain
City	Madrid
Period	9/18/95 → 9/21/95

ASJC Scopus subject areas

Computer Science Applications
Software
Linguistics and Language
Communication

Cite this

@conference{9b05b78421614a7f85a68aac4eada67a,

title = "SPEAKER ADAPTATION FITTING TRAINING DATA SIZE AND CONTENTS",

abstract = "This paper proposes a speaker adaptation algorithm that covers a wide range of adaptation data. The parameter smoothing technique improves adaptation performance for a small amount of adaptation data; however, this smoothing usually reduces adaptation efficiency for a large amount of adaptation data. Our method dynamically controls smoothing strength by using information on the amount of adaptation data to achieve good adaptation performance over a wide range of adaptation data. The proposed method is combined with the maximum a posteriori (MAP) estimation technique, and its effectiveness is shown on a Japanese 26 phoneme recognition test.",

author = "Masahiro Tonomura and Tetsuo Kosaka and Shoichi Matsunaga and Akito Monden",

note = "Publisher Copyright: {\textcopyright} 1995 4th European Conference on Speech Communication and Technology, EUROSPEECH 1995. All rights reserved.; 4th European Conference on Speech Communication and Technology, EUROSPEECH 1995 ; Conference date: 18-09-1995 Through 21-09-1995",

year = "1995",

language = "English",

pages = "1147--1150",

}

TY - CONF

T1 - SPEAKER ADAPTATION FITTING TRAINING DATA SIZE AND CONTENTS

AU - Tonomura, Masahiro

AU - Kosaka, Tetsuo

AU - Matsunaga, Shoichi

AU - Monden, Akito

PY - 1995

Y1 - 1995

N2 - This paper proposes a speaker adaptation algorithm that covers a wide range of adaptation data. The parameter smoothing technique improves adaptation performance for a small amount of adaptation data; however, this smoothing usually reduces adaptation efficiency for a large amount of adaptation data. Our method dynamically controls smoothing strength by using information on the amount of adaptation data to achieve good adaptation performance over a wide range of adaptation data. The proposed method is combined with the maximum a posteriori (MAP) estimation technique, and its effectiveness is shown on a Japanese 26 phoneme recognition test.

AB - This paper proposes a speaker adaptation algorithm that covers a wide range of adaptation data. The parameter smoothing technique improves adaptation performance for a small amount of adaptation data; however, this smoothing usually reduces adaptation efficiency for a large amount of adaptation data. Our method dynamically controls smoothing strength by using information on the amount of adaptation data to achieve good adaptation performance over a wide range of adaptation data. The proposed method is combined with the maximum a posteriori (MAP) estimation technique, and its effectiveness is shown on a Japanese 26 phoneme recognition test.

UR - http://www.scopus.com/inward/record.url?scp=85009059696&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009059696&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85009059696

SP - 1147

EP - 1150

T2 - 4th European Conference on Speech Communication and Technology, EUROSPEECH 1995

Y2 - 18 September 1995 through 21 September 1995

ER -

SPEAKER ADAPTATION FITTING TRAINING DATA SIZE AND CONTENTS

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this