Assem-vc: Realistic Voice Conversion By Assembling Modern Speech Synthesis Techniques
2021 · Kang-Wook Kim, Seung-Won Park, Junhyeok Lee, et al.
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.
Authors
(none)
Tags
Stats
Code
Related papers
- AC-VC: Non-parallel Low Latency Phonetic Posteriorgrams Based Voice Conversion (2021)7.50
- Starganv2-vc: A Diverse, Unsupervised, Non-parallel Framework For Natural-sounding Voice Conversion (2021)13.70
- Beyond Voice Identity Conversion: Manipulating Voice Attributes By Adversarial Learning Of Structured Disentangled Representations (2021)0.00
- Generative Adversarial Network Based Voice Conversion: Techniques, Challenges, And Recent Advancements (2025)0.00
- Fastvc: Fast Voice Conversion With Non-parallel Data (2020)5.24
- The Voice Conversion Challenge 2018: Promoting Development Of Parallel And Nonparallel Methods (2018)17.06
- Voicy: Zero-shot Non-parallel Voice Conversion In Noisy Reverberant Environments (2021)5.24
- Expressive-vc: Highly Expressive Voice Conversion With Attention Fusion Of Bottleneck And Perturbation Features (2022)9.03