VAW-GAN for Singing Voice Conversion with Non-parallel Training Data
arXiv:2008.03992
Abstract
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.
arXiv commentAccepted to APSIPA ASC 2020
References in corpus (9)
- Voice Conversion from Unaligned Corpora using Variational Autoencoding Wasserstein Generative Adversarial Networks
- F0-consistent many-to-many non-parallel voice conversion via conditional autoencoder
- Deep Encoder-Decoder Models for Unsupervised Learning of Controllable Speech Synthesis
- ACVAE-VC: Non-parallel many-to-many voice conversion with auxiliary classifier variational autoencoder
- An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learning
- Non-Parallel Voice Conversion with Cyclic Variational Autoencoder
- Converting Anyone's Emotion: Towards Speaker-Independent Emotional Voice Conversion
- Seen and Unseen emotional style transfer for voice conversion with a new emotional speech dataset
- WaveTTS: Tacotron-based TTS with Joint Time-Frequency Domain Loss