LightL2S: Ultra-Low Complexity Lip-to-Speech Synthesis for Multi-Speaker Scenarios

Yifan Liang, Kang Yang, Fangkun Liu, Andong Li, Xiaodong Li 0002, Chengshi Zheng. LightL2S: Ultra-Low Complexity Lip-to-Speech Synthesis for Multi-Speaker Scenarios. In Odette Scharenborg, Catharine Oertel, Khiet Truong, editors, 26th Annual Conference of the International Speech Communication Association, Interspeech 2025, Rotterdam, The Netherlands, 17-21 August 2025. ISCA, 2025. [doi]

@inproceedings{LiangYLLLZ25,
  title = {LightL2S: Ultra-Low Complexity Lip-to-Speech Synthesis for Multi-Speaker Scenarios},
  author = {Yifan Liang and Kang Yang and Fangkun Liu and Andong Li and Xiaodong Li 0002 and Chengshi Zheng},
  year = {2025},
  doi = {10.21437/Interspeech.2025-1478},
  url = {https://doi.org/10.21437/Interspeech.2025-1478},
  researchr = {https://researchr.org/publication/LiangYLLLZ25},
  cites = {0},
  citedby = {0},
  booktitle = {26th Annual Conference of the International Speech Communication Association, Interspeech 2025, Rotterdam, The Netherlands, 17-21 August 2025},
  editor = {Odette Scharenborg and Catharine Oertel and Khiet Truong},
  publisher = {ISCA},
}