Voice conversion (VC) modifies voice characteristics while preserving linguistic content. This paper presents the Stepback network, a novel model for converting speaker identity using non-parallel data. Unlike traditional VC methods that rely on parallel data, our approach leverages deep learning techniques to enhance disentanglement completion and linguistic content preservation. The Stepback network incorporates a dual flow of different domain data inputs and uses constraints with self-destructive amendments to optimize the content encoder. Extensive experiments show that our model significantly improves VC performance, reducing training costs while achieving high-quality voice conversion. The Stepback network's design offers a promising solution for advanced voice conversion tasks.
@article{arxiv.2501.15613,
title = {Stepback: Enhanced Disentanglement for Voice Conversion via Multi-Task Learning},
author = {Qian Yang and Calbert Graham},
journal= {arXiv preprint arXiv:2501.15613},
year = {2025}
}