Voice activity detection driven acoustic event classification for monitoring in smart homes

This contribution focuses on acoustic event detection and classification for monitoring of elderly people in ambient assistive living environments such as smart homes or nursing homes. We describe an autonomous system for robust detection of acoustic events in various practically relevant acoustic situations that benefits from a voice activity detection inspired preprocessing mechanism. Therefore, various already established voice activity detection schemes have been evaluated beforehand. As a specific use case, we address coughing as an acoustic event of interest which can be interpreted as an indicator for a potentially upcoming illness. After the detection of such events using a psychoacoustically motivated spectro-temporal representation (the so-called cochleogram), we forward its output to a statistical event modeling stage for automatic instantaneous emergency classification and long-term monitoring. The parameters derived by this procedure can then be used to inform medical or care-service personal.