Source code for INTERPSEECH 2023 paper: DuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic Model
You are welcome to take a look at our demo page!
A following work can be seen at Aty-TTS.
If you find the code useful for your research, please consider citing:
@inproceedings{wang23qa_interspeech,
author={Helin Wang and Thomas Thebaud and Jesús Villalba and Myra Sydnor and Becky Lammers and Najim Dehak and Laureano Moro-Velazquez},
title={{DuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic Model}},
year={2023},
booktitle={Proc. INTERSPEECH 2023},
pages={1548--1552},
doi={10.21437/Interspeech.2023-2203}
}@inproceedings{wang2023improving,
title={Improving fairness for spoken language understanding in atypical speech with Text-to-Speech},
author={Helin Wang and Venkatesh Ravichandran and Milind Rao and Becky Lammers and Myra Sydnor and Nicholas Maragakis and Ankur A. Butala and Jayne Zhang and Lora Clawson and Victoria Chovaz and Laureano Moro-Velazquez},
booktitle={NeurIPS 2023 Workshop on Synthetic Data Generation with Generative AI},
year={2023},
url={https://openreview.net/forum?id=YU228ZUCOU}
}
This repo is inspired by: