Free-energy Based Scoring for Speech Recognition

Traditionally, speech recognizers have used a strictly Bayesian paradigm for finding the best hypothesis from amongst all possible hypotheses for the data at hand that is to be recognized. In fact, the Bayes classification rule has been shown to be optimal when the class distributions represent the true distributions of the data to be classified. In reality, however, this condition is not satisfied the classifer itself is trained on some training data and may be deployed to recognize data that are different from the training data. The use of Enropy as an optimization criterion for various classification tasks has been well established in the literature. In our work, we show that free-energy, a thermodynamic concept directly related to enropy, can also be used as an objective criteion in classification. Furthermore, we show how this novel classification scheme can be used in the framework of existing Bayesian classification schemes implemented in current recognizers by simply modifying the class distributions a-priori. Pilot experiments performed under mismatched and matched conditions further bring out the viability for free-enrgy for classification in speech recognizers.