Automatic parameter extraction of fundamental frequency contours of speech based on a generative model

Author

Fujisaki, Hiroya ; OHNO, Sumio ; TOMITA, Osamu

Author_Institution

Dept. of Appl. Electron., Sci. Univ. of Tokyo, Japan

Volume

1

fYear

1996

fDate

14-18 Oct 1996

Firstpage

729

Abstract

The process of generating an F₀ contour from a small number of linguistically meaningful parameters, has been modeled quite accurately, and the model has been used extensively in speech synthesis. The paper deals with the inverse problem, i.e., that of extracting the model parameters from a given contour, which can only be solved by successive approximation. It presents a method for deriving a first-order approximation to a given F₀ contour from the linguistic information of the utterance, and refining the approximation by analysis-by-synthesis. The validity of the method has been confirmed experimentally

Keywords

approximation theory; feature extraction; inverse problems; linguistics; natural languages; parameter estimation; speech processing; speech synthesis; analysis by synthesis; automatic parameter extraction; experiment; first-order approximation; fundamental frequency contours; generative model; inverse problem; linguistic information; linguistically meaningful parameters; model parameters; speech generation; speech synthesis; successive approximation; Data mining; Electronic mail; Frequency; Information analysis; Inverse problems; Mathematical model; Natural languages; Parameter extraction; Speech processing; Speech synthesis;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing, 1996., 3rd International Conference on

Conference_Location

Beijing

Print_ISBN

0-7803-2912-0

Type

conf

DOI

10.1109/ICSIGP.1996.567366

Filename

567366