English

RefXVC: Cross-Lingual Voice Conversion with Enhanced Reference Leveraging

Audio and Speech Processing 2024-06-25 v1

Abstract

This paper proposes RefXVC, a method for cross-lingual voice conversion (XVC) that leverages reference information to improve conversion performance. Previous XVC works generally take an average speaker embedding to condition the speaker identity, which does not account for the changing timbre of speech that occurs with different pronunciations. To address this, our method uses both global and local speaker embeddings to capture the timbre changes during speech conversion. Additionally, we observed a connection between timbre and pronunciation in different languages and utilized this by incorporating a timbre encoder and a pronunciation matching network into our model. Furthermore, we found that the variation in tones is not adequately reflected in a sentence, and therefore, we used multiple references to better capture the range of a speaker's voice. The proposed method outperformed existing systems in terms of both speech quality and speaker similarity, highlighting the effectiveness of leveraging reference information in cross-lingual voice conversion. The converted speech samples can be found on the website: \url{http://refxvc.dn3point.com}

Keywords

Cite

@article{arxiv.2406.16326,
  title  = {RefXVC: Cross-Lingual Voice Conversion with Enhanced Reference Leveraging},
  author = {Mingyang Zhang and Yi Zhou and Yi Ren and Chen Zhang and Xiang Yin and Haizhou Li},
  journal= {arXiv preprint arXiv:2406.16326},
  year   = {2024}
}

Comments

Manuscript under review by TASLP

R2 v1 2026-06-28T17:16:46.985Z