Context-dependent environmental sound monitoring using SOM coupled with LEGION

Environmental sound measurement networks are increasingly applied for monitoring noise pollution in an urban context. Intelligent measurement nodes offer the opportunity to perform advanced analysis of environmental sound, but trade-offs between cost and functionality still have to be made. When using a tiered architecture, local nodes with limited computing capabilities can be used to detect sound events of potential interest, which are then further analyzed by more powerful nodes. This paper presents a human-mimicking model for detecting rare and conspicuous sound events. Features encoding spectro-temporal irregularities are extracted from the sound, and a Self-Organizing Map (SOM) is used to identify co-occurring features, which most likely belong to a single sound object. Extensive training allows this map to be tuned to the typical sounds that are heard at the microphone location. A Locally Excitatory Globally Inhibitory Oscillator Network (LEGION) is used to group units of the SOM in order to construct distinct sound objects