Here is a link to our generated samples.
-
Link to GAN voice conversion model.
-
Link to VAE voice conversion model.
-
We used REAPER and Rubber Band to build our signal processing approach. Details are described in our paper.
-
Run
src/main.pyto train the adversary classifier. -
Link to ASR model.
Understanding the Tradeoffs in Client-side Privacy for Downstream Speech Tasks
@inproceedings{wu2021privacy,
title={Understanding the Tradeoffs in Client-side Privacy for Downstream Speech Tasks},
author={Peter Wu and Paul Pu Liang and Jiatong Shi and Ruslan Salakhutdinov and Shinji Watanabe and Louis-Philippe Morency},
booktitle={APSIPA ASC},
year={2021}
}
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent