Curriculum-Based Noise Adaptation for Phoneme-to-Text Reconstruction in Visual Speech Recognition
PECT consistently improves reconstruction performance across multiple phoneme-based visual speech recognition frontends, including visual automatic speech recognition (V-ASR), point visual automatic speech recognition (PV-ASR), and head-pose-aware visual speech recognition (HP-VSR) variants.
Matthew Kit Khinn Teng, Hai-Bo Zhang, Takeshi Saitoh
· 0 citations