A Machine Learning-Based Approach for Audio Signals Classification using Chebychev Moments and Mel-Coefficients

This paper proposes a machine learning-based architecture for audio signals classification based on a joint exploitation of the Chebychev moments and the Mel-Frequency Cepstrum Coefficients. The procedure starts with the computation of the Mel-spectrogram of the recorded audio signals; then, Chebychev moments are obtained projecting the Cadence Frequency Diagram derived from the Mel-spectrogram into the base of Chebychev moments. These moments are then concatenated with the Mel-Frequency Cepstrum Coefficients to form the final feature vector. By doing so, the architecture exploits the peculiarities of the discrete Chebychev moments such as their symmetry characteristics. The effectiveness of the procedure is assessed on two challenging datasets, UrbanSound8K and ESC-50.