Classification of traffic-related sounds with machine learning methods

Drivers' safety and comfort have been improved over the decades through new technologies and driver modelling studies that expand understanding of predicting driver behaviour. Despite the notable advances in autonomous and interactive systems, there is a significant lack of approaches that treat passengers and the vehicle as components of a dynamic vibro-acoustic system. Sound in vehicles not only provides information about the vehicle's condition and environment but can also affect the driver's performance, attention and driving pleasure. This thesis aims to investigate the interaction between the perceived sounds of a vehicle and measures of psychoacoustic disturbance. Keywords: Psychoacoustic Metrics, Acoustic-Driven, Deep Reinforcement Learning, Safety.