Audio-Visual Speech Recognition (AVSR) and lip reading have emerged as pivotal research areas that integrate auditory and visual modalities to enhance the robustness of speech recognition systems. By ...

Learning visual speech representations from talking face videos is an important problem for several speech-related tasks, such as lip reading, talking face generation, audio-visual speech separation, ...

Deafness creates significant barriers to speech development as it prevents the brain from receiving essential auditory feedback needed for learning speech. While cochlear implants can be effective ...