Speech Recognition Using Dynamic Time Warping

Shashikant R. Thite; Daulappa G. Bhalke

Speech Recognition Using Dynamic Time Warping

Shashikant R. Thite ¹, Daulappa G. Bhalke ²

Affiliations
1 Department of Electronics & Telecommunication, JSPM's Rajarshi Shahu College of Engg., Tathawade, Pune, India
2 Department of Electronics & Telecommunication, JSPM's Rajarshi Shahu College of Engg., Tathawade, India

In this paper, we discuss an speech recognition based on dynamic time-warping for image retrieval. The DTW-algorithm originates from the field of speech recognition. We claim that the results of a recognizer based on the DTW-algorithm template matching are more "intuitive" to humans than the results of other recognizers. We use MFCC for feature extraction. It is proposed that higher recognition rates can be achieved using MFCC features with DTW. ASM FCC coefficient increases the accuracy also increases.