An Efficient Method for Removing Deletion Errors in Quickly-spoken Connected Mandarin Digit String Speech Recognition

Connected Mandarin digit string speech, especially at rapid spoken rate, is very difficult to recognize correctly. In this paper, a new training method named neighboring digits pattern is proposed in order to eliminate most of deletion errors which frequently occur in Mandarin digits speech recognition at high speaking rate when we have enough quickly-spoken speech data as the training set. The complete implementation process and the corresponding data analysis are presented detailed and the performance is compared with that of the conventional system through the experiments. The results of comparison explain that the new method can reduce the deletion errors effectively, and thus improves the system recognition rate from 96.4% to 98.3%.