한국음향학회:학술대회논문집 (Proceedings of the Acoustical Society of Korea Conference)
- 한국음향학회 1994년도 제11회 음성통신 및 신호처리 워크샵 논문집 (SCAS 11권 1호)
- /
- Pages.407-410
- /
- 1994
A STUDY ON THE SIMULATED ANNEALING OF SELF ORGANIZED MAP ALGORITHM FOR KOREAN PHONEME RECOGNITION
- Kang, Myung-Kwang (Dept. of Computer Engineering Kwang-Woon Univ.) ;
- Ann, Tae-Ock (Dept. of Computer Engineering Chon Buk Sanup Univ.) ;
- Kim, Lee-Hyung (Dept. of Computer Engineering Kwang-Woon Univ.) ;
- Kim, Soon-Hyob (Dept. of Computer Engineering Chon Buk Sanup Univ.)
- 발행 : 1994.06.01
초록
In this paper, we describe the new unsuperivised learning algorithm, SASOM. It can solve the defects of the conventional SOM that the state of network can't converge to the minimum point. The proposed algorithm uses the object function which can evaluate the state of network in learning and adjusts the learning rate flexibly according to the evaluation of the object function. We implement the simulated annealing which is applied to the conventional network using the object function and the learning rate. Finally, the proposed algorithm can make the state of network converged to the global minimum. Using the two-dimensional input vectors with uniform distribution, we graphically compared the ordering ability of SOM with that of SASOM. We carried out the recognitioin on the new algorithm for all Korean phonemes and some continuous speech.
키워드