Activating accessible pedestrian signals by voice using keyword spotting systems

摘要

We describe the problem of partially sighted pedestrians who identify crossing the street as a difficult task. Pedestrian call buttons remain difficult to activate for partially sighted pedestrians. We believe that human-technology interfaces such as speech-related technologies can help to make this task easier. We propose a deep learning model for keyword spotting system where pedestrians can activate the pedestrian call button using their voice and thus enable them to cross the streets safely.