EUVIMEDEUVIMED entdecken
Crossref

Challenges in self-supervised speech representation-based voice conversion

Wen-Chin Huang

The Journal of the Acoustical Society of America · 01.10.2025 · 158 (4_Supplement) · A259-A259

DOI: 10.1121/10.0040816 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, erschienen am 01.10.2025. Verfasst von Wen-Chin Huang.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Self-supervised learning has revolutionized all speech processing fields, and voice conversion was no exception. Using self-supervised speech representations such as HuBERT and WavLM has become the de facto in voice conversion tasks. However, the great success is often demonstrated under constrained conditions, typically involving read speech from English speakers. In this talk, I will first provide an overview of a typical self-supervised speech representation-based voice conversion framework. I will then highlight key challenges that remain to be addressed, including speaker information leakage, temporal structure modeling, and the application to more complex tasks such as accent conversion and singing voice conversion. These ongoing efforts aim to push the boundaries of what is possible with voice conversion in diverse and real-world scenarios.

Zitieren

APA

Huang, W. (2025). Challenges in self-supervised speech representation-based voice conversion. The Journal of the Acoustical Society of America, 158(4_Supplement), A259-A259. https://doi.org/10.1121/10.0040816

Vancouver

Huang W. Challenges in self-supervised speech representation-based voice conversion. The Journal of the Acoustical Society of America. 2025;158(4_Supplement):A259-A259. doi:10.1121/10.0040816

BibTeX
@article{Huang2025,
  author = {Huang, Wen-Chin},
  title = {Challenges in self-supervised speech representation-based voice conversion},
  journal = {The Journal of the Acoustical Society of America},
  year = {2025},
  volume = {158},
  number = {4_Supplement},
  pages = {A259--A259},
  doi = {10.1121/10.0040816}
}
Kostenlos starten →