English

Boosting Star-GANs for Voice Conversion with Contrastive Discriminator

Audio and Speech Processing 2022-09-28 v4 Artificial Intelligence Machine Learning Sound

Abstract

Nonparallel multi-domain voice conversion methods such as the StarGAN-VCs have been widely applied in many scenarios. However, the training of these models usually poses a challenge due to their complicated adversarial network architectures. To address this, in this work we leverage the state-of-the-art contrastive learning techniques and incorporate an efficient Siamese network structure into the StarGAN discriminator. Our method is called SimSiam-StarGAN-VC and it boosts the training stability and effectively prevents the discriminator overfitting issue in the training process. We conduct experiments on the Voice Conversion Challenge (VCC 2018) dataset, plus a user study to validate the performance of our framework. Our experimental results show that SimSiam-StarGAN-VC significantly outperforms existing StarGAN-VC methods in terms of both the objective and subjective metrics.

Keywords

Cite

@article{arxiv.2209.10088,
  title  = {Boosting Star-GANs for Voice Conversion with Contrastive Discriminator},
  author = {Shijing Si and Jianzong Wang and Xulong Zhang and Xiaoyang Qu and Ning Cheng and Jing Xiao},
  journal= {arXiv preprint arXiv:2209.10088},
  year   = {2022}
}

Comments

12 pages, 3 figures, Accepted by ICONIP 2022

R2 v1 2026-06-28T01:47:06.986Z