Conditional Deep Hierarchical Variational Autoencoder for Voice Conversion

no code implementations • 6 Dec 2021 • Kei Akuzawa, Kotaro Onishi, Keisuke Takiguchi, Kohki Mametani, Koichiro Mori

Variational autoencoder-based voice conversion (VAE-VC) has the advantage of requiring only pairs of speeches and speaker labels for training.

Decoder Voice Conversion

Investigating context features hidden in End-to-End TTS

no code implementations • 4 Nov 2018 • Kohki Mametani, Tsuneo Kato, Seiichi Yamamoto

Recent studies have introduced end-to-end TTS, which integrates the production of context and acoustic features in statistical parametric speech synthesis.

Feature Engineering Speech Synthesis