Classification of environmental audio signals using statistical time and frequency features

In this paper, we present an approach for location classification that does not need to have an explicit information about the place, in contrast with systems such as a Quick Response Code (QR) or Radio Frequency Identificator tag. Our approach consists of using an “audio fingerprint” of the environmental background sounds of the place. We propose a fingerprint that consists of a set of 62 audio features, which are from temporal, frequency and statistical features. To conform an audio fingerprint, a feature extraction process was performed. We apply the feature extraction process over 70 environmental sounds of 14 different places to conform each audio fingerprint. To demonstrate the effectiveness of the set of features, we evaluate the set of features with two different classifiers: Random Forest and Support Vector Machine. Our results indicate that using this set of features allow us to classify a place with an accuracy of 84.28% for Random Forest and 91.42% for Support Vector Machine.