Wavelet classification of indoor environmental sound sources

Abstract

Computational auditory scene analysis (CASA) has been attracting growing interest since the publication of Bregman's text on human auditory scene analysis, and is expected to find many applications in data retrieval, autonomous robots, security and environmental analysis. This paper reports on the use of Fourier transforms and wavelet transforms to produce spectral data of sounds from different sources for classification by neural networks. It was found that the multiresolution time-frequency analyses of wavelet transforms dramatically improved classification accuracy when statistical descriptors that captured measures of band limited spectral energy and temporal energy fluctuation were used.