Assem-VC: Realistic Voice Conversion by Assembling Modern Speech Synthesis Techniques [article]

Kang-wook Kim, Seung-won Park, Junhyeok Lee, Myun-chul Joe
2021 arXiv   pre-print
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
more » ... e speaker identity with adversarial training. Code and audio samples are available at https://github.com/mindslab-ai/assem-vc.
arXiv:2104.00931v2 fatcat:yxvyss4zireutmcquc4pkmpniy