DocumentCode
302305
Title
Voice conversion using partitions of spectral feature space
Author
Verhelst, Werner ; Mertens, Johan
Author_Institution
Fac. of Appl. Sci., Vrije Univ., Brussels, Belgium
Volume
1
fYear
1996
fDate
7-10 May 1996
Firstpage
365
Abstract
Given a set of utterances that have been spoken by two speakers, the problem of voice conversion consists in constructing some sort of transformation that can be applied on any utterance of the first speaker and makes the result appear to have been spoken by the second speaker. Conversion rules for the vocal tract spectral characteristics, which are usually trained on individual subsets of a partition of the spectral feature space, still do not reach the desired level of accuracy. The paper presents an analysis of the problem
Keywords
spectral analysis; speech synthesis; conversion rules; speakers; spectral feature space partitions; text to speech synthesis; transformation; utterances; vocal tract spectral characteristics; voice conversion; Automatic control; Control systems; Databases; Filters; Loudspeakers; Spectrogram; Speech synthesis; Telephony; Timbre; Wideband;
fLanguage
English
Publisher
ieee
Conference_Titel
Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference on
Conference_Location
Atlanta, GA
ISSN
1520-6149
Print_ISBN
0-7803-3192-3
Type
conf
DOI
10.1109/ICASSP.1996.541108
Filename
541108
Link To Document