Probabilistic integration of joint density model and speaker model for voice conversion

This paper describes a novel approach to voice conversion using both a joint density model and a speaker model. In voice conversion studies, approaches based on Gaussian Mixture Model (GMM) with probabilistic densities of joint vectors of a source and a target speakers are widely used to estimate a transformation. However, for sufficient quality, they require a parallel corpus which contains plenty of utterances with the same linguistic content spoken by both the speakers. In addition, the joint density GMM methods often suffer from over-training effects when the amount of training data is small. To compensate for these problems, we propose a novel approach to integrate the speaker GMM of the target with the joint density model using probabilistic formulation. The proposed method trains the joint density model with a few parallel utterances, and the speaker model with non-parallel data of the target, independently. It eases the burden on the source speaker. Experiments demonstrate the...

• Type: Journal
• Year: 2010
• Where: INTERSPEECH
• Authors: Daisuke Saito, Shinji Watanabe, Atsushi Nakamura, Nobuaki Minematsu
• Keywords: INTERSPEECH 2010, Joint Density, Joint Density Model, Signal Processing, Speaker Model