Cross-language voice conversion

Author

Abe, Masanobu ; Shikano, Kiyohiro ; Kuwabara, Hisao

Author_Institution

ATR Interpreting Telephony Res. Lab., Kyoto, Japan

fYear

1990

fDate

3-6 Apr 1990

Firstpage

345

Abstract

First, the part of spectral difference that is due to the difference in language is assessed. This is investigated using a bilingual speaker´s speech data. It is found that the interlanguage (between English and Japanese) difference is smaller than the interspeaker difference. Listening tests indicate that the difference between English and Japanese is very small. Second, a model for cross-language voice conversion is described. In this approach, voice conversion is considered a mapping problem between two speakers´ spectrum spaces. The spectrum spaces are represented by codebooks. From this point of view, a cross-language voice conversion model and measures for the model are proposed. The converted speech from male to female is as understandable as the unconverted speech and, moreover, it is recognized as female speech

Keywords

encoding; spectral analysis; speech analysis and processing; speech recognition; English; Japanese; bilingual speaker; codebooks; converted speech; cross-language voice conversion; cross-language voice conversion model; female speech; interlanguage; interspeaker difference; male speech; mapping problem; spectral difference; spectrum spaces; speech data; unconverted speech; Character generation; Control system synthesis; Laboratories; Loudspeakers; Natural languages; Speech recognition; Speech synthesis; Telephony; Testing; Vector quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on

Conference_Location

Albuquerque, NM

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1990.115676

Filename

115676