Title :
Speech recognition using the metric defined by integra-normalizer
Author :
Kim, Sung-Soo ; Lee, Dae-Jong ; Kwark, Keun-Chang ; Kim, Ju-Sik ; Ryu, Jeong-Woong ; Lee, Sang-Hyuk
Author_Institution :
Dept. of Electr. Eng., Woosuk Univ., South Korea
Abstract :
This paper represents a new method of recognizing speech using the metric defined by integra-normalizer (IN). A neuro-fuzzy method is also demonstrated as a comparison to the proposed method. A codebook is constructed with a set of feature vectors extracted from the raw speech data. There are various schemes for measuring the distance between a set of information. In this paper, the distance between feature vectors is obtained by using the new metric defined by IN. The metric by IN possesses an advantage to the conventional metrics such as the metric defined by the least square error in L2 or in l2 spaces. With the approach proposed, the information on the patterns of the speech features is mapped to the feature vectors and the metric measures the difference between speech patterns considering the shape of patterns. The results of the computer simulation are shown for the validity of this proposed method
Keywords :
adaptive systems; backpropagation; feature extraction; fuzzy neural nets; least squares approximations; speech recognition; adaptive neuro-fuzzy inference system; backpropagation; codebook; computer simulation results; distance measurement; feature vectors extraction; fuzzy rule generation; integra-normalizer defined metric; least square error; neuro-fuzzy method; speech data; speech features; speech patterns shape; speech recognition; Automatic speech recognition; Automation; Computer simulation; Electrical safety; Feature extraction; Least squares approximation; Shape; Signal processing; Speech processing; Speech recognition;
Conference_Titel :
Industrial Electronics, 2001. Proceedings. ISIE 2001. IEEE International Symposium on
Conference_Location :
Pusan
Print_ISBN :
0-7803-7090-2
DOI :
10.1109/ISIE.2001.931961
