An online model adaptation method for compensating speech models for noise in continuous speech recognition

This paper presents a method for online model adaptation based on the parallel model combination (PMC) method. The proposed method makes use of the concept of Gaussian model clustering to reduce the computation load required by PMC. This model clustering, in combination with a set of derived transformation equations, provide a potential framework for online model adaptation in noisy speech recognition. The proposed method reduces the computation in adaptation by about 45% with only a slight degradation in improvements of an average 18% for a connected digit task and 9% for a large vocabulary Mandarin task when compared with standard PMC method.