EUVIMEDEUVIMED entdecken
Crossref

TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching

Wenxiang Guo, Yu Zhang, Changhao Pan, Rongjie Huang, Li Tang, Ruiqi Li, Zhiqing Hong, Yongqi Wang, Zhou Zhao

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (22) · 23978-23986

DOI: 10.1609/aaai.v39i22.34571 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Wenxiang Guo und 8 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Singing voice synthesis has made remarkable progress in generating natural and high-quality voices. However, existing methods rarely provide precise control over vocal techniques such as intensity, mixed voice, falsetto, bubble, and breathy tones, thus limiting the expressive potential of synthetic voices. We introduce TechSinger, an advanced system for controllable singing voice synthesis that supports five languages and seven vocal techniques. TechSinger leverages a flow-matching-based generative model to produce singing voices with enhanced expressive control over various techniques. To enhance the diversity of training data, we develop a technique detection model that automatically annotates datasets with phoneme-level technique labels. Additionally, our prompt-based technique prediction model enables users to specify desired vocal attributes through natural language, offering fine-grained control over the synthesized singing. Experimental results demonstrate that TechSinger significantly enhances the expressiveness and realism of synthetic singing voices, outperforming existing methods in terms of audio quality and technique-specific control.

Zitieren

APA

Guo, W., Zhang, Y., Pan, C., Huang, R., Tang, L., Li, R., Hong, Z., Wang, Y., & Zhao, Z. (2025). TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching. Proceedings of the AAAI Conference on Artificial Intelligence, 39(22), 23978-23986. https://doi.org/10.1609/aaai.v39i22.34571

Vancouver

Guo W, Zhang Y, Pan C, Huang R, Tang L, Li R, et al. TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(22):23978-23986. doi:10.1609/aaai.v39i22.34571

BibTeX
@article{Guo2025,
  author = {Guo, Wenxiang and Zhang, Yu and Pan, Changhao and Huang, Rongjie and Tang, Li and Li, Ruiqi and Hong, Zhiqing and Wang, Yongqi and Zhao, Zhou},
  title = {TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {22},
  pages = {23978--23986},
  doi = {10.1609/aaai.v39i22.34571}
}
Kostenlos starten →