Assem-VC: Realistic Voice Conversion by Assembling Modern Speech Synthesis Techniques
Audio and Speech Processing
2021-10-12 v2 Machine Learning
Sound
Abstract
Recent works on voice conversion (VC) focus on preserving the rhythm and the intonation as well as the linguistic content. To preserve these features from the source, we decompose current non-parallel VC systems into two encoders and one decoder. We analyze each module with several experiments and reassemble the best components to propose Assem-VC, a new state-of-the-art any-to-many non-parallel VC system. We also examine that PPG and Cotatron features are speaker-dependent, and attempt to remove speaker identity with adversarial training. Code and audio samples are available at https://github.com/mindslab-ai/assem-vc.
Keywords
Cite
@article{arxiv.2104.00931,
title = {Assem-VC: Realistic Voice Conversion by Assembling Modern Speech Synthesis Techniques},
author = {Kang-wook Kim and Seung-won Park and Junhyeok Lee and Myun-chul Joe},
journal= {arXiv preprint arXiv:2104.00931},
year = {2021}
}