Computation and Parameter Efficient Multi-Modal Fusion Transformer for Cued Speech Recognition

Cued Speech (CS) is a pure visual coding method used by hearing-impaired people that combines lip reading with several specific hand shapes to make the spoken language visible. Automatic CS recognition (ACSR) seeks to transcribe visual cues of speech into text, which can help hearing-impaired people to communicate effectively. The visual information of CS contains lip reading and hand cueing, thus the fusion of them plays an important role in ACSR. However, most previous fusion methods struggle to capture the …

coding computation cs.cv cs.sd eess.as fusion hearing language lip reading modal multi-modal people reading recognition speech speech recognition spoken text transcribe transformer visual visual cues