A pattern recognition system for environmental sound classification based on MFCCs and neural networks

The paper proposes a study of a background noise classifier based on a pattern recognition approach using a neural network. The signals submitted to the neural network are characterised by means of a set of 12 MFCC (Mel frequency cepstral coefficient) parameters typically present in the front end of a mobile terminal. The performance of the classifier, evaluated in terms of percent misclassification, indicate an accuracy ranging between 73% and 95% depending on the duration of the decision window.