LIKELIHOOD DECISION BOUNDARY ESTIMATION BETWEEN HMM PAIRS IN SPEECH RECOGNITION

In maximum likelihood (ML) estimation of hidden Markov models (HMM's) for speech recognition, the criterion is to maximize the total probabi lity across the training data for a particular speech unit, such as a word, monophone, diphone, or triphone. Since each unit model is traine d separately, such a strategy can often lead to biases among decision boundaries of the generated model set. In this correspondence, we prop ose a new technique to minimize the total number of misclassifications in the training data set by adjusting the decision boundaries between HMM pairs. The proposed algorithm is shown to reduce the error rate i n a number of speech recognition tasks such as accent detection, langu age identification, and confusable word pair discrimination. The techn ique is also attractive because it is simple to implement and the impr ovement in performance is achieved without any added complexity in the decoding phase.