VAW-GAN for Singing Voice Conversion with Non-parallel Training Data
This addresses the challenge of singing voice conversion for real-life applications where parallel data is impractical, though it is incremental as it builds on existing encoder-decoder structures.
The paper tackles the problem of singing voice conversion without requiring parallel training data by proposing a framework based on VAW-GAN, which disentangles singer identity and prosody from phonetic content and achieves better performance than baseline frameworks.
Singing voice conversion aims to convert singer's voice from source to target without changing singing content. Parallel training data is typically required for the training of singing voice conversion system, that is however not practical in real-life applications. Recent encoder-decoder structures, such as variational autoencoding Wasserstein generative adversarial network (VAW-GAN), provide an effective way to learn a mapping through non-parallel training data. In this paper, we propose a singing voice conversion framework that is based on VAW-GAN. We train an encoder to disentangle singer identity and singing prosody (F0 contour) from phonetic content. By conditioning on singer identity and F0, the decoder generates output spectral features with unseen target singer identity, and improves the F0 rendering. Experimental results show that the proposed framework achieves better performance than the baseline frameworks.