Probabilistic classification of HMM states for large vocabulary continuous speech recognition

In state-of-art large vocabulary continuous speech recognition (LVCSR) systems, HMM state-tying is often used to achieve good balance between the model resolution and robustness. In this paradigm, tied HMM states share a single set of parameters and are nondistinguishable. To capture the fine differences among tied HMM states, a probabilistic classification of HMM states (PCHMM) is proposed in this paper for LVCSR. In particular, a distribution from a HMM state to classes is introduced. It is shown that the state-to-class distribution can be estimated together with conventional HMM parameters within the EM [3] framework. Compared with HMM state-tying, probabilistic classification of HMM states makes more efficient use of model parameters. It also makes the acoustic model more robust against the possible mismatch or variation between training and test data. The viability of this approach is verified by the significant reduction of word error rate (WER) on the Switchboard [7] task.