Voice conversion using nonlinear principal component analysis

Author

Makki, B. ; Seyedsalehi, S.A. ; Sadati, N. ; Hosseini, M. Noori

Author_Institution

Dept. of Biomed. Eng., Amirkabir Univ. of Technol., Tehran

fYear

2007

fDate

1-5 April 2007

Firstpage

336

Lastpage

339

Abstract

In the last decades, much attention has been paid to the design of multi-speaker voice conversion. In this work, a new method for voice conversion (VC) using nonlinear principal component analysis (NLPCA) is presented. The principal components are extracted and transformed by a feed-forward neural network which is trained by combination of genetic algorithm (GA) and back-propagation (BP). Common pre- and post-processing approaches are applied to increase the quality of the synthesized speech. The results indicate that the proposed method can be considered as a step towards multi-speaker voice conversion

Keywords

backpropagation; feedforward neural nets; genetic algorithms; principal component analysis; speech coding; speech synthesis; backpropagation; feedforward neural network; genetic algorithm; multispeaker voice conversion; nonlinear principal component analysis; speech synthesis; Biomedical engineering; Computational intelligence; Feedforward systems; Hidden Markov models; Image converters; Neural networks; Principal component analysis; Signal processing; Speech synthesis; Virtual colonoscopy;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence in Image and Signal Processing, 2007. CIISP 2007. IEEE Symposium on

Conference_Location

Honolulu, HI

Print_ISBN

1-4244-0707-9

Type

conf

DOI

10.1109/CIISP.2007.369191

Filename

4221441