Influence of several audio parameters in urban sound event classification

This paper presents a system for recognition and classification of sound events established through the development of processes for detection and parameterization of sound signals that are used for further classification by applying machine learning algorithms. The focus is on the feature extraction process and the accuracy achieved when using different audio parameters. Five audio parameters were analyzed and tested on three machine learning algorithms order to investigate their influence in recognizing the class of the disturbing sound events in the urban areas, thus yielding to a collection of 48 different combinations. The applied audio parameters: MFCC, Mel Spectrogram, Chromagram, Spectral Contrast and Tonal Centroid were chosen as they are widely used for urban noise classification, but their combination forming diverse feature vectors have not been still analyzed. The accuracy results were different for each combination of the audio parameters, thus leading to choosing best set of parameters that reach the highest recognition accuracy. The used algorithms: Random Forest (RF), Naïve Bayes (NB) and Support Vector Machines (SVM) classifier are chosen as they have shown very efficient classification in the field of urban noise recognition.