Hierarchical disentangled representation learning for singing voice conversion

01/18/2021
by   Naoya Takahashi, et al.
20

Conventional singing voice conversion (SVC) methods often suffer from operating in high-resolution audio owing to a high dimensionality of data. In this paper, we propose a hierarchical representation learning that enables the learning of disentangled representations with multiple resolutions independently. With the learned disentangled representations, the proposed method progressively performs SVC from low to high resolutions. Experimental results show that the proposed method outperforms baselines that operate with a single resolution in terms of mean opinion score (MOS), similarity score, and pitch accuracy.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset