ÇѱÛÁ¦¸ñ(Korean Title) |
Àº´Ð ¸¶¸£ÄÚÇÁ ¸ðµ¨ÀÇ È®·üÀû ÃÖÀûȸ¦ ÅëÇÑ ÀÚµ¿ µ¶¼øÀÇ ¼º´É Çâ»ó |
¿µ¹®Á¦¸ñ(English Title) |
Improved Automatic Lipreading by Stochastic Optimization of Hidden Markov Models |
ÀúÀÚ(Author) |
ÀÌÁ¾¼®
¹ÚöÈÆ
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 14-B NO. 07 PP. 0523 ~ 0530 (2007. 12) |
Çѱ۳»¿ë (Korean Abstract) |
º» ³í¹®¿¡¼´Â ÀÚµ¿ µ¶¼ø(automatic lipreading)ÀÇ Àνıâ·Î ¾²ÀÌ´Â Àº´Ð ¸¶¸£ÄÚÇÁ ¸ðµ¨(HMM: hidden Markov model)ÀÇ »õ·Î¿î È®·üÀû ÃÖÀûÈ ±â¹ýÀ» Á¦¾ÈÇÑ´Ù. Á¦¾ÈÇÏ´Â ±â¹ýÀº Àü¿ª ÃÖÀûÈ°¡ °¡´ÉÇÑ È®·üÀû ±â¹ýÀÎ ¸ðÀÇ ´ã±ÝÁú°ú Áö¿ª ÃÖÀûÈ ±â¹ýÀ» °áÇÕÇÏ´Â °ÍÀ¸·Î½á, ¾Ë°í¸®ÁòÀÇ ºü¸¥ ¼ö·Å°ú ÁÁÀº ÇØ·ÎÀÇ ¼ö·ÅÀ» °¡´ÉÇÏ°Ô ÇÑ´Ù. Á¦¾ÈÇÏ´Â ¾Ë°í¸®ÁòÀÌ Àü¿ª ÃÖÀûÇØ·Î ¼ö·ÅÇÔÀ» ¼öÇÐÀûÀ¸·Î º¸ÀδÙ. Á¦¾ÈÇÏ´Â ±â¹ýÀ» ÅëÇØ HMMÀ» ÇнÀÇÔÀ¸·Î½á ±âÁ¸ÀÇ ¾Ë°í¸®ÁòÀÌ Áö¿ªÇظ¸À» ã´Â ´ÜÁ¡À» °³¼±ÇÔÀ¸·Î½á Çâ»óµÈ µ¶¼ø ¼º´ÉÀ» ³ªÅ¸³¿À» ½ÇÇèÀ¸·Î º¸ÀδÙ.
|
¿µ¹®³»¿ë (English Abstract) |
This paper proposes a new stochastic optimization algorithm for hidden Markov models (HMMs) used as a recognizer of automatic lipreading. The proposed method combines a global stochastic optimization method, the simulated annealing technique, and the local optimization method, which produces fast convergence and good solution quality. We mathematically show that the proposed algorithm converges to the global optimum. Experimental results show that training HMMs by the method yields better lipreading performance compared to the conventional training methods based on local optimization.
|
Å°¿öµå(Keyword) |
ÀÚµ¿ µ¶¼ø
Àº´Ð ¸¶¸£ÄÚÇÁ ¸ðµ¨
È®·üÀû ÃÖÀûÈ
Àü¿ª ÃÖÀûÈ
¸ðÀÇ ´ã±ÝÁú
Automatic Lipreading
Hidden Markov Model
Stochastic Optimization
Global Optimization
Simulated Annealing
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|