Model adaptation method for recognition of speech with missing frames.

In distributed speech recognition (DSR), data packets may be lost over error prone channels. A commonly used approach to rectify this is to reconstruct a full frame rate data sequence for recognition using linear interpolation. In this study, an error-concealment decoding method that dynamically adapts the transition probabilities of hidden Markov models to match the frame loss observation sequence is proposed. Experimental results show that a DSR system using the proposed method can achieve the same level of accuracy as a data reconstruction method, is more robust against heavy frame loss, and significantly reduces the computation time.