A novel spiral pattern and 2D M4 pooling based environmental sound classification method

Abstract

One of the crucial problems of the signal processing, digital forensics and machine learning is the environmental sound classification (ESC). Several ESC methods have been presented to obtain highly accurate model. In this work, a novel multileveled ESC method is presented. The presented ESC method uses two novel algorithms namely Spiral Pattern and two dimensional maximum, minimum, median and mean (2D-M4) pooling. By using these methods (Spiral Pattern and 2D-M4 pooling), 9 level feature generation approach is presented. Since the proposed Spiral Pattern has nine arrows, it extracts 9 and 18 bits using signum and ternary functions respectively. As a result, 1536 features are extracted in each level and totally 15,360 features are generated using from 0th to 9th levels. In order to select the discriminative features, neighbourhood component analysis (NCA) is used and 700 most distinctive features are selected. In the classification phase, deep neural network is trained and tested with the ESC-10 and ESC-50 datasets. 98.75% and 85.75% average classification accuracies were achieved with 10-folds cross validation for ESC-10 and ESC-50 datasets respectively. The experimental results reveal that the proposed Spiral Pattern and 2D-M4 pooling based ESC method is superior than the human auditory system (HAS) for environmental sound classification.