Skip to content

An unofficial PyTorch implementation of "Cross-Speaker Emotion Disentangling and Transfer for End-to-End Speech Synthesis"

Notifications You must be signed in to change notification settings

woaki/tacotron-edm

Repository files navigation

This is an unofficial PyTorch implementation of Cross-Speaker Emotion Disentangling and Transfer for End-to-End Speech Synthesis. Feel free to use/modify the code.

Quickstart

Dependencies

You can install the Python dependencies with

pip3 install -r requirements.txt

Implementation Issues

Please inform me if you find any mistakes in this repo, or any useful tips to train a more emotional TTS model. Additionally, I would greatly appreciate it if the paper's author could share the original code.

References

Citation

@ARTICLE{9747987,
  author={Li, Tao and Wang, Xinsheng and Xie, Qicong and Wang, Zhichao and Xie, Lei},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, 
  title={Cross-Speaker Emotion Disentangling and Transfer for End-to-End Speech Synthesis}, 
  year={2022},
  volume={30},
  number={},
  pages={1448-1460},
  doi={10.1109/TASLP.2022.3164181}
}

About

An unofficial PyTorch implementation of "Cross-Speaker Emotion Disentangling and Transfer for End-to-End Speech Synthesis"

Resources

Stars

Watchers

Forks