A maximum-likelihood approach to stochastic matching for robust speech recognition

Presents a maximum-likelihood (ML) stochastic matching approach to decrease the acoustic mismatch between a test utterance and a given set of speech models so as to reduce the recognition performance degradation caused by distortions in the test utterance and/or the model set. We assume that the speech signal is modeled by a set of subword hidden Markov models (HMM) Λ_x. The mismatch between the observed test utterance Y and the models Λ_x can be reduced in two ways: 1) by an inverse distortion function F_ν (.) that maps Y into an utterance X that matches better with the models Λ_x and 2) by a model transformation function G _η(.) that maps Λ_x to the transformed model Λ_x that matches better with the utterance Y. We assume the functional form of the transformations F_ν(.) or G_η(.) and estimate the parameters ν or η in a ML manner using the expectation-maximization (EM) algorithm. The choice of the form of F_ν(.) or G_η(.) is based on prior knowledge of the nature of the acoustic mismatch. The stochastic matching algorithm operates only on the given test utterance and the given set of speech models, and no additional training data is required for the estimation of the mismatch prior to actual testing. Experimental results are presented to study the properties of the proposed algorithm and to verify the efficacy of the approach in improving the performance of a HMM-based continuous speech recognition system in the presence of mismatch due to different transducers and transmission channels