An MRNN-based method for continuous Mandarin speech recognition

Abstract

A new MRNN-based method for continuous Mandarin speech recognition is proposed. The system uses five RNNs to accomplish many subtasks separately and then combine them to integrally solve the problem. They include two RNNs for the discriminations of the two sub-syllable groups of 100 RFD initials and 39 CI finals, two RNNs for the generations of dynamic weighting functions for sub-syllable's integration, and one RNN for syllable boundary detection. All RNN modules are combined using a delay-decision Viterbi search. The method differs from the ANN/HMM hybrid approach on using ANNs to perform not only sub-syllables discrimination but also temporal structure modeling of speech signal. The system is trained using a three-stage training method embedding with the MCE/GPD algorithms. Besides, fast recognition method using multi-level pruning is also proposed. Experimental results showed that it outperforms the HMM method on both the recognition accuracy and the computational complexity.