Comparison of Decoder-based Transmission Error Compensation Techniques for Distributed Speech Recognition

In this study we evaluate transmission error compensation techniques for distributed speech recognition systems based on modification of the speech decoder. The candidates are marginalization, weighted Viterbi and our recently proposed soft-feature uncertainty decoding. For the latter, it is shown how the Bayesian speech recognition approach must be reformulated for recognition at the server side. The resulting predictive classifier is able to take account of the transmission errors by changing the contribution of the affected speech features to the acoustic score. The comparison of the experimental results has proven the superiority of our approach.