Voice conversion using nonlinear principal component analysis

B. Makki, S.A. Seyedsalehi, N. Sadati, M. Noori Hosseini
2007 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing  
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.
more » ... results indicate that the proposed method can be considered as a step towards multi-speaker voice conversion.
doi:10.1109/ciisp.2007.369191 fatcat:rsetvm6wpzhdjpxgrrucviq6m4