ARTICULATORY MODEL AND THE ESTIMATION OF ARTICULATORY PARAMETERS BY NONLINEAR REGRESSION METHOD.

Katsuhiko Shirai, Masaaki Honda

研究成果: Chapter

8 引用 (Scopus)

抄録

It is important to investigate articulatory motion to obtain fundamental knowledge in speech communication, speech synthesis and speech recognition. The characteristics of articulatory motion should thus be reflected in data processing in the acoustic domain. For this purpose it is desirable to establish a suitable model of the articulatory mechanism. This paper introduces a new method of constructing such a model. The special feature of this model is representation of the variation of the tongue shape using principal components obtained by the analysis of X-ray data. This permits more accurate description of the articulation than the usual models using the same number of parameters. Correspondences between the articulatory parameters and the acoustic features are calculated in this model and the results are applied for estimation of the articulatory parameters by a nonlinear regression method. Results obtained by estimation from the formant frequencies are successfully applied to synthesized and real voices and show the validity of this method.

元の言語English
ホスト出版物のタイトルElectron Commun Jpn
ページ35-43
ページ数9
59
エディション8
出版物ステータスPublished - 1976 8
外部発表Yes

Fingerprint

Acoustics
Speech communication
Speech synthesis
Speech recognition
X rays

ASJC Scopus subject areas

  • Engineering(all)

これを引用

ARTICULATORY MODEL AND THE ESTIMATION OF ARTICULATORY PARAMETERS BY NONLINEAR REGRESSION METHOD. / Shirai, Katsuhiko; Honda, Masaaki.

Electron Commun Jpn. 巻 59 8. 編 1976. p. 35-43.

研究成果: Chapter

@inbook{2c59c674c4a24d0089ef08d90f7e95b5,
title = "ARTICULATORY MODEL AND THE ESTIMATION OF ARTICULATORY PARAMETERS BY NONLINEAR REGRESSION METHOD.",
abstract = "It is important to investigate articulatory motion to obtain fundamental knowledge in speech communication, speech synthesis and speech recognition. The characteristics of articulatory motion should thus be reflected in data processing in the acoustic domain. For this purpose it is desirable to establish a suitable model of the articulatory mechanism. This paper introduces a new method of constructing such a model. The special feature of this model is representation of the variation of the tongue shape using principal components obtained by the analysis of X-ray data. This permits more accurate description of the articulation than the usual models using the same number of parameters. Correspondences between the articulatory parameters and the acoustic features are calculated in this model and the results are applied for estimation of the articulatory parameters by a nonlinear regression method. Results obtained by estimation from the formant frequencies are successfully applied to synthesized and real voices and show the validity of this method.",
author = "Katsuhiko Shirai and Masaaki Honda",
year = "1976",
month = "8",
language = "English",
volume = "59",
pages = "35--43",
booktitle = "Electron Commun Jpn",
edition = "8",

}

TY - CHAP

T1 - ARTICULATORY MODEL AND THE ESTIMATION OF ARTICULATORY PARAMETERS BY NONLINEAR REGRESSION METHOD.

AU - Shirai, Katsuhiko

AU - Honda, Masaaki

PY - 1976/8

Y1 - 1976/8

N2 - It is important to investigate articulatory motion to obtain fundamental knowledge in speech communication, speech synthesis and speech recognition. The characteristics of articulatory motion should thus be reflected in data processing in the acoustic domain. For this purpose it is desirable to establish a suitable model of the articulatory mechanism. This paper introduces a new method of constructing such a model. The special feature of this model is representation of the variation of the tongue shape using principal components obtained by the analysis of X-ray data. This permits more accurate description of the articulation than the usual models using the same number of parameters. Correspondences between the articulatory parameters and the acoustic features are calculated in this model and the results are applied for estimation of the articulatory parameters by a nonlinear regression method. Results obtained by estimation from the formant frequencies are successfully applied to synthesized and real voices and show the validity of this method.

AB - It is important to investigate articulatory motion to obtain fundamental knowledge in speech communication, speech synthesis and speech recognition. The characteristics of articulatory motion should thus be reflected in data processing in the acoustic domain. For this purpose it is desirable to establish a suitable model of the articulatory mechanism. This paper introduces a new method of constructing such a model. The special feature of this model is representation of the variation of the tongue shape using principal components obtained by the analysis of X-ray data. This permits more accurate description of the articulation than the usual models using the same number of parameters. Correspondences between the articulatory parameters and the acoustic features are calculated in this model and the results are applied for estimation of the articulatory parameters by a nonlinear regression method. Results obtained by estimation from the formant frequencies are successfully applied to synthesized and real voices and show the validity of this method.

UR - http://www.scopus.com/inward/record.url?scp=0016986557&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0016986557&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:0016986557

VL - 59

SP - 35

EP - 43

BT - Electron Commun Jpn

ER -