Phoneme-Level Visual Speech Recognition via Point-Visual Fusion and Language Model Reconstruction 文章

ArXiv CS.CV2026-06-02NEWSen作者: Matthew Kit Khinn Teng, Haibo Zhang, Takeshi Saitoh
查看原文 →
关系图谱

Phoneme-Level Visual Speech Recognition via Point-Visual Fusion and Language Model Reconstruction · 相关技术

相关技术

LLMautomatic speech recognition