CPL - Chalmers Publication Library
| Utbildning | Forskning | Styrkeområden | Om Chalmers | In English In English Ej inloggad.

Voice Conversion Using Nonlinear Principal Component Analysis

Behrooz Makki (Institutionen för signaler och system, Kommunikationssystem) ; Seyedali Seyedsalehi ; Nasser Sadati ; Mona Noori Hosseini
IEEE symposium series on computational intelligence Vol. 1 (2007), 1, p. 336-339.
[Konferensbidrag, refereegranskat]

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

Nyckelord: voice conversion; nonlinear principal component analysis; genetic algorithm

Denna post skapades 2009-02-25. Senast ändrad 2017-10-03.
CPL Pubid: 90433


Läs direkt!

Länk till annan sajt (kan kräva inloggning)

Institutioner (Chalmers)

Institutionen för signaler och system, Kommunikationssystem (1900-2017)


Elektroteknik och elektronik

Chalmers infrastruktur