Environmental sound recognition using Gaussian mixture model and neural network classifier

Environmental sound recognition is an audio scene identification process in which a person´s location is found by analyzing the background sound. This paper deals with the prototype modeling for environmental sound recognition. Sound recognition involves the collection of audio data, extraction of important features, clustering of similar features and their classification. The Mel frequency cepstrum co-efficients are extracted. These features are used for clustering by a Gaussian mixture model which is a probabilistic model. Neural Network classifier is used for classification of the features and to identify the environmental audio scene. The implementation is done with the help of MATLAB. Five major environmental sounds which include the sound of car, office, restaurant, street, subway are considered. This shows a better efficiency than the already existing method. The efficiency achieved in this method is 98.9%.