The goal of the repository is to provide an implementation of the WaveNet vocoder, which can generate high quality raw speech samples conditioned on linguistic or acoustic features.
Audio sampels are available at https://github.com/r9y9/wavenet_vocoder.
This is still WIP. See r9y9#1 for planned TODOs and current progress.
- Aaron van den Oord, Sander Dieleman, Heiga Zen, et al, "WaveNet: A Generative Model for Raw Audio", arXiv:1609.03499, Sep 2016.
- Aaron van den Oord, Yazhe Li, Igor Babuschkin, et al, "Parallel WaveNet: Fast High-Fidelity Speech Synthesis", arXiv:1711.10433, Nov 2017.
- Tamamori, Akira, et al. "Speaker-dependent WaveNet vocoder." Proceedings of Interspeech. 2017.
- Jonathan Shen, Ruoming Pang, Ron J. Weiss, et al, "Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions", arXiv:1712.05884, Dec 2017.
- Wei Ping, Kainan Peng, Andrew Gibiansky, et al, "Deep Voice 3: 2000-Speaker Neural Text-to-Speech", arXiv:1710.07654, Oct. 2017.