This repository is the wavenet-vocoder implementation with pytorch.

• Support kaldi-like recipe, easy to reproduce the results

• Support multi-gpu training / decoding

• Support world features / mel-spectrogram as auxiliary features

• Support recipes of three public databases

  • CMU Arctic database: egs/arctic
  • LJ Speech database: egs/ljspeech
  • M-AILABS speech database: egs/m-ailabs-speech

• python 3.6
• virtualenv
• cuda 8.0
• cndnn 6
• nccl 2.0+ (for the use of multi-gpus)

Recommend to use the GPU with 10GB> memory.

$ git clone https://github.com/kan-bayashi/PytorchWaveNetVocoder.git
$ cd PytorchWaveNetVocoder/tools
$ make

$ cd egs/arctic/sd
$ ./run.sh

See more detail of the recipes in egs/README.md.

This is the subjective evaluation results using arctic recipe.

You can listen the samples generated by our models from here.

• arctic_raw_16k.wav: original in arctic database
• arctic_sd_16k_world.wav: sd model with world aux feats + noise shaping with world mcep
• arctic_si-open_16k_world.wav: si-open model with world aux feats + noise shaping with world mcep
• arctic_si-close_16k_world.wav: si-close model with world aux feats + noise shaping with world mcep
• arctic_si-close_16k_melspc.wav: si-close model with mel-spectrogram aux feats
• arctic_si-close_16k_melspc_ns.wav: si-close model with mel-spectrogram aux feats + noise shaping with stft mcep
• ljspeech_raw_22.05k.wav: original in ljspeech database
• ljspeech_sd_22.05k_world.wav: sd model with world aux feats + noise shaping with world mcep
• ljspeech_sd_22.05k_melspc.wav: sd model with mel-spectrogram aux feats
• ljspeech_sd_22.05k_melspc_ns.wav: sd model with mel-spectrogram aux feats + noise shaping with stft mcep
• m-ailabs_raw_16k.wav: original in m-ailabs speech database
• m-ailabs_sd_16k_melspc.wav: sd model with mel-spectrogram aux feats

Please cite the following articles.

@inproceedings{tamamori2017speaker,
  title={Speaker-dependent WaveNet vocoder},
  author={Tamamori, Akira and Hayashi, Tomoki and Kobayashi, Kazuhiro and Takeda, Kazuya and Toda, Tomoki},
  booktitle={Proceedings of Interspeech},
  pages={1118--1122},
  year={2017}
}
@inproceedings{hayashi2017multi,
  title={An Investigation of Multi-Speaker Training for WaveNet Vocoder},
  author={Hayashi, Tomoki and Tamamori, Akira and Kobayashi, Kazuhiro and Takeda, Kazuya and Toda, Tomoki},
  booktitle={Proc. ASRU 2017},
  year={2017}
}
@article{hayashi2018sp,
  title={複数話者WaveNetボコーダに関する調査}.
  author={林知樹 and 小林和弘 and 玉森聡 and 武田一哉 and 戸田智基},
  journal={電子情報通信学会技術研究報告},
  year={2018}
}

Tomoki Hayashi @ Nagoya University
e-mail:[email protected]