Developing speech recognition in public transportation for universally designed information flow

Abstract

Today, information in public transport is largely provided through speakers. This is especially true in unforeseen events, such as signal failures, platform change and in emergencies such as fire, evacuation and the like. Such situations are often chaotic, and the driver / conductor / pilot is reading messages about what happens and what passengers are going to do. This rarely helps the hearing impaired to bring along. There is therefore a need for a system that recognizes the speech to the driver / conductor / pilot and translates speech to text on screen. And this thesis has explained the procedure and possibilities of creating such a system for the public transportation system.