Experiments in female voice speech synthesis using a parametric articulatory model

Author

Wei, Dongbing ; Goodyear, C.C.

Author_Institution

Dept. of Electr. Eng. & Electron., Liverpool Univ., UK

Volume

3

fYear

1997

fDate

21-24 Apr 1997

Firstpage

1631

Abstract

A parametric vocal tract model and a two dimensional articulatory parametric subspace for a female voice are presented. The parameters of the model, which determine the vocal tract shape, can be found uniquely for VV transitions by mapping directly from f1 and f2 onto this subspace, while a modified technique involving f3 is available for voiced VC and CV diphones. The area functions of the vocal tract, generated by these parameters, are used to drive a time-domain synthesiser. Synthesis to give female speech, copied from either male or female natural speech, may be performed

Keywords

parameter estimation; speech intelligibility; speech processing; speech synthesis; 2D articulatory parametric subspace; VV transitions; area functions; experiments; f1; f2; f3; female natural speech; female voice speech synthesis; formant frequencies; male natural speech; modified technique; parametric articulatory model; parametric vocal tract model; speech quality; subspace; time-domain synthesiser; vocal tract shape; voiced CV diphones; voiced VC diphones; Computational efficiency; Interpolation; Larynx; Magnetic resonance imaging; Natural languages; Shape; Speech synthesis; Time domain analysis; Tongue; Virtual colonoscopy;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on

Conference_Location

Munich

ISSN

1520-6149

Print_ISBN

0-8186-7919-0

Type

conf

DOI

10.1109/ICASSP.1997.598816

Filename

598816