Time Domain Adversarial Voice Conversion for ADD 2022
Audio and Speech Processing
2022-04-21 v2 Cryptography and Security
Sound
Abstract
In this paper, we describe our speech generation system for the first Audio Deep Synthesis Detection Challenge (ADD 2022). Firstly, we build an any-to-many voice conversion (VC) system to convert source speech with arbitrary language content into the target speaker%u2019s fake speech. Then the converted speech generated from VC is post-processed in the time domain to improve the deception ability. The experimental results show that our system has adversarial ability against anti-spoofing detectors with a little compromise in audio quality and speaker similarity. This system ranks top in Track 3.1 in the ADD 2022, showing that our method could also gain good generalization ability against different detectors.
Keywords
Cite
@article{arxiv.2204.08692,
title = {Time Domain Adversarial Voice Conversion for ADD 2022},
author = {Cheng Wen and Tingwei Guo and Xingjun Tan and Rui Yan and Shuran Zhou and Chuandong Xie and Wei Zou and Xiangang Li},
journal= {arXiv preprint arXiv:2204.08692},
year = {2022}
}
Comments
Accepted to ICASSP 2022