A Multi-Resolution Approach for Audio Classification

We describe a multi-resolution approach for audio classification and illustrate its application to the open data set for environmental sound classification. The proposed approach utilizes a multi-resolution based ensemble consisting of targeted feature extraction of approximation (coarse scale) and detail (fine scale) portions of the signal under the action of multiple transforms. This is paired with an automatic machine learning engine for algorithm and parameter selection and the LSTM algorithm, capable of mapping several sequences of features to a predicted class membership probability distribution. A conditional probability approach is outlined for combining the predictions of different classifiers, trained over distinct scale feature sets. Initial results show an improvement in multi-class classification accuracy.