Mixture of Factor Analyzers Using Priors from Non-Parallel Speech for Voice Conversion

Zhizheng Wu, Tomi Kinnunen, E. S. Chng, Haizhou Li

Research output: Contribution to journalArticlepeer-review

Abstract

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 nonparallel 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.
Original languageEnglish
Pages (from-to)914-917
Number of pages4
JournalIEEE Signal Processing Letters
Volume19
Issue number12
DOIs
Publication statusPublished - 2012

Fingerprint

Dive into the research topics of 'Mixture of Factor Analyzers Using Priors from Non-Parallel Speech for Voice Conversion'. Together they form a unique fingerprint.

Cite this