ICASSP2020-demo

"Teacher-Student Training for Robust Tacotron-based TTS",

Authors: Rui Liu, Berrak Sisman, Jingdong Li, Feilong Bao, Guanglai Gao, Haizhou Li

This paper was accepted by ICASSP2020

paper

Speech samples

Examples of synthesized speech by "Tacotron2-SS" , "Tacotron2-FR" and "Tacotron2-KD" systems.

Speech samples are available at demo page.

Tacotron2-FR: Tacotron2-based model with free running (FR) mode

Tacotron2-SS: Tacotron2-based model with scheduled sampling (SS) mode

Tacotron2-KD: Tacotron2-based model with proposed teacher-student training method by using knowledge distillation (KD)

Reference

Please kindly cite this paper in your publications if it helps your research:

@INPROCEEDINGS{9054681,
  author={Liu, Rui and Sisman, Berrak and Li, Jingdong and Bao, Feilong and Gao, Guanglai and Li, Haizhou},
  booktitle={ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
  title={Teacher-Student Training For Robust Tacotron-Based TTS}, 
  year={2020},
  volume={},
  number={},
  pages={6274-6278},
  doi={10.1109/ICASSP40776.2020.9054681}}

:)