Audio clip classification using LP residual and neural networks models

In this paper, we demonstrate the presence of audio-specific information in the linear prediction (LP) residual, obtained after removing the predictable part of the signal. We emphasize the importance of information present in the LP residual of audio signals, which if added to the spectral information, can give a better performing system. Since it is difficult to extract information from the residual using known signal processing algorithms, neural networks (NN) models are proposed. In this paper, autoassociative neural networks (AANN) models are used to capture the audio-specific information from the LP residual of signals. Multilayer feedforward neural networks (MLFFNN) models or multilayer perceptron (MLP) are used to classify the audio data using the audio-specific information captured by AANN models.