Use of a self-learning neuro-fuzzy system for syllabic labeling of continuous speech

For reducing the requirement of large memory and minimizing computation complexity in a large-vocabulary continuous speech recognition system, speech segmentation plays an important role. In this paper, the authors formulate the speech segmentation as a two-phase problem. Phase 1 (frame labelling) involves labeling frames of speech data. Frames are classified into three types: (1) silence; (2) consonants; and (3) vowels according to two segmentation features. In phase 2 (syllabic unit segmentation) the authors apply the concept of transition states to segment continuous speech data into syllabic units based on the labeled frames. The novel class of hyperrectangular composite neural networks (HRCNs) is used to cluster frames. The HRCNNs integrate the rule-based approach and neural network paradigms, therefore, this special hybrid system may neutralize the disadvantages of each alternative. The parameters in the trained HRCNNs are utilized to extract both crisp and fuzzy classification rules. Four speakers´ continuous reading-rate Mandarin speech are given to illustrate the proposed two-phase speech segmentation model. In the authors´ experiments, the performance of the HRCNNs is better than the “distributed fuzzy rule” approach based on the comparisons of the number of rules and the correct recognition rate