Audio Classification with Thermodynamic Criteria

Abstract

Detecting sound events in audio recordings is a challenging problem. A detector must be trained for each sound to be classified. However, the recordings of the examples used to train the detector rarely match the conditions found in the test audio to be classified. If the event detection problem is posed as one of Bayes classification, the problem may be viewed as one of mismatch between the true distribution of the data and that represented by the classifier. The Bayes classification rule results in suboptimal performance under such mismatch, and a modified classification rule is required. Alternately stated, the classification rule must optimize a different objective criterion than the Bayes error rate computed from the training distributions. The use of entropy as an optimization criterion for various classification tasks has been well established in the literature. In this paper we show that free-energy, a thermodynamic concept directly related to entropy, can also be used as an objective criterion for classification in such scenarios. We demonstrate with examples on classification with HMMs that minimization of free-energy is an effective criterion for classification under conditions of mismatch.