EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FastTalk: Speech-Driven Lip Synchronization Video Generation for Chinese-Language Scenarios

Yizhang Liu, Tao Fan, Xu Zhao, Guozhong Wang

Applied Sciences · 01.05.2026 · 16 (9) · 4438

DOI: 10.3390/app16094438 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 01.05.2026. Verfasst von Yizhang Liu und 3 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Speech-driven lip synchronization is an important technique for talking-face video generation, with broad application potential in virtual humans, video dubbing, digital media, and human–computer interaction. However, existing methods still face challenges in achieving reliable lip synchronization while maintaining stable identity preservation, high visual fidelity, and efficient inference, especially in Chinese-language scenarios where related research remains relatively limited. To address these issues, we propose FastTalk, a speech-driven lip synchronization method for Chinese-language scenarios. The proposed framework performs latent-space restoration for efficient video synthesis, uses a fixed-mask strategy to suppress shortcut visual cues and strengthen audio-driven lip-shape prediction, and adopts a two-stage training scheme to reduce the gap between training and inference. This design improves generation stability while preserving efficiency. Experimental results show that FastTalk achieves competitive lip synchronization performance while improving visual quality and identity preservation. These results indicate that FastTalk provides an effective solution for Chinese speech-driven lip synchronization video generation.

Zitieren

APA

Liu, Y., Fan, T., Zhao, X., & Wang, G. (2026). FastTalk: Speech-Driven Lip Synchronization Video Generation for Chinese-Language Scenarios. Applied Sciences, 16(9), 4438. https://doi.org/10.3390/app16094438

Vancouver

Liu Y, Fan T, Zhao X, Wang G. FastTalk: Speech-Driven Lip Synchronization Video Generation for Chinese-Language Scenarios. Applied Sciences. 2026;16(9):4438. doi:10.3390/app16094438

BibTeX
@article{Liu2026,
  author = {Liu, Yizhang and Fan, Tao and Zhao, Xu and Wang, Guozhong},
  title = {FastTalk: Speech-Driven Lip Synchronization Video Generation for Chinese-Language Scenarios},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {9},
  pages = {4438},
  doi = {10.3390/app16094438}
}
Kostenlos starten →