Á¤º¸°úÇÐȸ ³í¹®Áö A : ½Ã½ºÅÛ ¹× ÀÌ·Ð
ÇѱÛÁ¦¸ñ(Korean Title) |
ÀÔ¼ú ¾Ö´Ï¸ÞÀ̼ÇÀ» À§ÇÑ ÇÑ±Û ¹ßÀ½ÀÇ µ¿½ÃÁ¶À½ ¸ðµ¨ |
¿µ¹®Á¦¸ñ(English Title) |
Coarticulation Model of Hangul Visual Speech for Lip Animation |
ÀúÀÚ(Author) |
°ø±¤½Ä
±èâÇå
Kwang-Sik Kong
Chang-Hun Kim
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 26 NO. 09 PP. 1031 ~ 1041 (1999. 09) |
Çѱ۳»¿ë (Korean Abstract) |
±âÁ¸ÀÇ Çѱۿ¡ ´ëÇÑ ÀÔ¼ú ¾Ö´Ï¸ÞÀÌ¼Ç ¹æ¹ýÀº À½¼ÒÀÇ ÀÔ¸ð¾çÀ» ¸î °³ÀÇ ÀÔ¸ð¾çÀ¸·Î Á¤ÀÇÇÏ°í À̵éÀ» º¸°£ÇÏ¿© ÀÔ¼úÀ» ¾Ö´Ï¸ÞÀ̼ÇÇÏ¿´´Ù. ÇÏÁö¸¸ ¹ßÀ½ÇÏ´Â µ¿¾ÈÀÇ ½ÇÁ¦ ÀÔ¼ú ¿òÁ÷ÀÓÀº ¼±ÇüÇÔ¼ö³ª ´Ü¼øÇÑ ºñ¼±ÇüÇÔ¼ö°¡ ¾Æ´Ï±â ¶§¹®¿¡ º¸°£¹æ¹ý¿¡ ÀÇÇØ Áß°£ ¿òÁ÷ÀÓÀ» »ý¼ºÇÏ´Â ¹æ¹ýÀ¸·Î´Â À½¼ÒÀÇ ÀÔ¼ú ¿òÁ÷ÀÓÀ» È¿°úÀûÀ¸·Î »ý¼ºÇÒ ¼ö ¾ø´Ù. ¶Ç ÀÌ ¹æ¹ýÀº µ¿½ÃÁ¶À½µµ °í·ÁÇÏÁö ¾Ê¾Æ À½¼Òµé°£¿¡ º¯ÈÇÏ´Â ÀÔ¼ú ¿òÁ÷ÀÓµµ Ç¥ÇöÇÒ ¼ö ¾ø¾ú´Ù. º» ³í¹®¿¡¼´Â µ¿½ÃÁ¶À½À» °í·ÁÇÏ¿© ÇѱÛÀ» ÀÚ¿¬½º·´°Ô ¹ßÀ½ÇÏ´Â ÀÔ¼ú ¾Ö´Ï¸ÞÀÌ¼Ç ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. ºñµð¿À Ä«¸Þ¶ó·Î ¹ßÀ½ÇÏ´Â µ¿¾ÈÀÇ À½¼ÒÀÇ ¿òÁ÷ÀÓµéÀ» ÃøÁ¤ÇÏ°í ÀÔ¼ú ¿òÁ÷ÀÓ Á¦¾î ÆĶó¹ÌÅ͵éÀ» ÃßÃâÇÑ´Ù. °¢°¢ÀÇ Á¦¾î ÆĶó¹ÌÅ͵éÀº LofqvistÀÇ ½ºÇÇÄ¡ »ý¼º Á¦½ºÃ³ ÀÌ·Ð(speech production gesture theory)À» ÀÌ¿ëÇÏ¿© ½ÇÁ¦ À½¼ÒÀÇ ÀÔ¼ú ¿òÁ÷ÀÓ¿¡ ±Ù»çÇÑ ¿òÁ÷ÀÓÀÎ Áö¹èÇÔ¼ö(dominance function)µé·Î Á¤Àǵǰí ÀÔ¼ú ¿òÁ÷ÀÓÀ» ¾Ö´Ï¸ÞÀ̼ÇÇÒ ¶§ »ç¿ëµÈ´Ù. ¶Ç, °¢ Áö¹èÇÔ¼öµéÀº È¥ÇÕÇÔ¼ö(blending function)¿Í ¹ÝÀ½Àý¿¡ ÀÇÇÑ ÇÑ±Û ÇÕ¼º ±ÔÄ¢À» »ç¿ëÇÏ¿© °áÇÕÇÏ°í µ¿½ÃÁ¶À½ÀÌ Àû¿ëµÈ ÇѱÛÀ» ¹ßÀ½ÇÏ°Ô µÈ´Ù. µû¶ó¼ ½ºÇÇÄ¡ »ý¼º Á¦½ºÃ³ ÀÌ·ÐÀ» ÀÌ¿ëÇÏ¿© ÀÔ¼ú ¿òÁ÷ÀÓ ¸ðµ¨À» ±¸ÇöÇÑ ¹æ¹ýÀº ±âÁ¸ÀÇ º¸°£¿¡ ÀÇÇØ Áß°£ ¿òÁ÷ÀÓÀ» »ý¼ºÇÑ ¹æ¹ýº¸´Ù ½ÇÁ¦ ¿òÁ÷ÀÓ¿¡ ±Ù»çÇÔ ¿òÁ÷ÀÓÀ» »ý¼ºÇÏ°í µ¿½ÃÁ¶À½µµ °í·ÁÇÑ ¿òÁ÷ÀÓÀ» º¸¿©ÁØ´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
The existing lip animation method of Hangul classifies the shape of lips with a few shapes and implements the lip animation with interpolating them. However it doesn't represent natural lip animation because the function of the real motion of lips, during articulation, isn't linear or simple non-linear function. It doesn't also represent the motion of lips varying among phonemes because it doesn't consider coarticulation. In this paper we present a new coarticulation model for the natural lip animation of Hangul. Using two video cameras, we film the speaker's lips and extract the lip control parameters. Each lip control parameter is defined as dominance function by using Lofqvist's speech production gesture theory. This dominance function approximates to the real lip animation of a phoneme during articulation of one and is used when lip animation is implemented. Each dominance function combines into blending function by using Hangul composition rule based on demi-syllable. Then the lip animation of our coarticulation model represents natural motion of lips. Therefore our coarticulation model approximates to real lip motion rather than the existing model and represents the natural lip motion considered coarticulation.
|
Å°¿öµå(Keyword) |
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|