Mixture of factor analyzers using priors from non-parallel speech for voice conversion

A robust voice conversion function relies on a large amount of parallel training data, which is difficult to collect in practice. To tackle the sparse parallel training data problem in voice conversion, this paper describes a mixture of factor analyzers method which integrates prior knowledge from n...

Full description

Bibliographic Details
Published in:IEEE Signal Processing Letters
Main Authors: Wu, Zhizheng, Kinnunen, Tomi, Chng, Eng Siong, Li, Haizhou
Other Authors: School of Computer Engineering, Temasek Laboratories
Format: Article in Journal/Newspaper
Language:English
Published: 2013
Subjects:
DRNTU::Engineering::Computer science and engineering
Arctic
Online Access:https://hdl.handle.net/10356/102726
http://hdl.handle.net/10220/16436
https://doi.org/10.1109/LSP.2012.2225615
Description
Summary:A robust voice conversion function relies on a large amount of parallel training data, which is difficult to collect in practice. To tackle the sparse parallel training data problem in voice conversion, this paper describes a mixture of factor analyzers method which integrates prior knowledge from non-parallel speech into the training of conversion function. The experiments on CMU ARCTIC corpus show that the proposed method improves the quality and similarity of converted speech. With both objective and subjective evaluations, we show the proposed method outperforms the baseline GMM method.

Similar Items