Noise robust speech recognition with state duration constraints

In this paper, we present a method to incorporate and re-estimate state duration constraints within the maximum likelihood training of hidden Markov models. In the recognition phase we find the optimal state sequence fulfilling the state duration constraints obtained in the training phase. Our target is to get speaker-dependent training and recognition to perform well with a very small amount of training data in the case of mismatch between the training and testing environments. We take advantage of the fact that speakers tend to preserve their speaking style in similar situations (e.g. when speaking to a machine) and our main means to reach the target is to force similar state segmentations in the training and recognition phases. We show that with the proposed method we can substantially improve the robustness of a speech recognizer and decrease the error rates by over 93% when compared with a standard approach.