Modeling Articulatory Movements for Voice Conversion Using State-Space Model

In this paper, we present a new voice conversion method based on the state-space model (SSM). A modified version of the conventional SSM model is first proposed to describe the relationship between the source speech and the target speech in the spectral domain. Then the expectation maximum (EM) and variational Bayesian (VB) algorithms are individually employed to estimate the SSM parameters, resulting in two different schemes of the estimation of SSM parameters. Owing to the intrinsic feature of the SSM that is suitable for the modeling of the articulatory movement of speech signals, the proposed SSM-based method significantly outperforms the traditional GMM-based method. Experiments using both objective and subjective measurements are conducted to validate the effectiveness of the proposed method.