An automated environmental sound classification methods based on statistical and textural feature

Abstract

Determining the location from environmental sounds is crucial for digital forensics. Therefore, it is possible to predict about the sounds obtained using the automatic environmental sound classification (ESC) method. In this study, a method has been proposed for classifying environmental sounds. The main objective of this paper is to present a high accurate stable feature extraction based ESC method. This method consists of 3 fundamental stages and these are feature generation, selecting feature and classification stages. One dimensional local binary pattern (1D-LBP), One dimensional ternary pattern (1D-TP) and statistical feature generation methods are used for feature extraction. Neighborhood component analysis is used to select discriminative features and cubic (3rd Polynomial Order Kernel) support vector machine is used for classification. The proposed method is applied on ESC-10 dataset and the classification of the sounds on the dataset has been provided. 90.25% accuracy rate is obtained with the proposed method. A novel cognitive, high accurate and lightweight ESC method is presented in this work. In addition, comparison with previous studies is presented. The proposed method is outperformed.