Curriculum-Based Noise Adaptation for Phoneme-to-Text Reconstruction in Visual Speech Recognition

Excerpt

arXiv:2609.20839v1 Announce Type: new Abstract: Phoneme-centric visual speech recognition reconstructs sentences from intermediate phoneme predictions, making overall recognition performance highly dependent on the robustness of the phoneme-to-text reconstruction model. Existing reconstruction approaches are commonly trained on clean phoneme sequences or synthetically corrupted inputs, leading to a mismatch between training conditions and the realistic phoneme prediction errors encountered durin