Instrument for soundscape recognition, identification and evaluation (ISRIE): Signal classification

Abstract

ISRIE is a collaborative project between the universities of York and Newcastle and ISVR in Southampton. The work being undertaken at York is in its second year and focuses on signal separation and classification. Developing novel methods for classifying urban and other sounds into distinct categories (such as transportation, industrial, human, animal, etc.) is the focus of the work detailed in this paper. The classification system will initially consist of 2 main parts: a feature extractor and a classifier. Results from this basic system will be presented and a discussion given on how the system will be expanded. It is envisaged that eventually the system will use some form of syntactic pattern recognition to perform the identification of individual sounds.