Reducing computational complexity of dynamic time warping-based isolated word recognition with time scale modification

In this paper, we propose an algorithm to reduce the computational complexity of dynamic time warping for isolated speech recognition. Prior to the feature extraction process in speech recognition, we apply time scale compression both on the reference and testing utterances. Experimental results show that the computational complexity can be reduced by up to 75% without affecting the accuracy of recognition. The time scale process can also suppress the effect of noise to a certain degree so that the recognition accuracy can be improved for noisy test utterances. The proposed algorithm can solve the problem of high mismatch of utterance duration between two utterances.