摘要：Consonant(in Chinese) recognition had important clinical significance in the assessment of dysarthria, while the consonants were so short and unstable that the recognition results of traditional methods were ineffective. The algorithm described in this paper extracted a new feature(DWTMFC-CT) of the consonants employing wavelet transformation, and the difference of similar consonants can be described more accurately by the feature. Then the algorithm classified consonants using multi-class fuzzy support vector machines(FSVM). In order to reduce the computation complexity caused by using the standard fuzzy support vector machines for multi-class classification, this paper proposed a algorithm based on two stages. Experimental results shown that the proposed algorithm could get better classification results while reducing the training time greatly.
