English

PseudoVC: Improving One-shot Voice Conversion with Pseudo Paired Data

Audio and Speech Processing 2025-06-03 v1 Sound

Abstract

As parallel training data is scarce for one-shot voice conversion (VC) tasks, waveform reconstruction is typically performed by various VC systems. A typical one-shot VC system comprises a content encoder and a speaker encoder. However, two types of mismatches arise: one for the inputs to the content encoder during training and inference, and another for the inputs to the speaker encoder. To address these mismatches, we propose a novel VC training method called \textit{PseudoVC} in this paper. First, we introduce an innovative information perturbation approach named \textit{Pseudo Conversion} to tackle the first mismatch problem. This approach leverages pretrained VC models to convert the source utterance into a perturbed utterance, which is fed into the content encoder during training. Second, we propose an approach termed \textit{Speaker Sampling} to resolve the second mismatch problem, which will substitute the input to the speaker encoder by another utterance from the same speaker during training. Experimental results demonstrate that our proposed \textit{Pseudo Conversion} outperforms previous information perturbation methods, and the overall \textit{PseudoVC} method surpasses publicly available VC models. Audio examples are available.

Keywords

Cite

@article{arxiv.2506.01039,
  title  = {PseudoVC: Improving One-shot Voice Conversion with Pseudo Paired Data},
  author = {Songjun Cao and Qinghua Wu and Jie Chen and Jin Li and Long Ma},
  journal= {arXiv preprint arXiv:2506.01039},
  year   = {2025}
}

Comments

5 pages, 3 figures

R2 v1 2026-07-01T02:53:12.268Z