• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö

Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ´ëÈ­ ¿µ»ó »ý¼ºÀ» À§ÇÑ Çѱ¹¾î °¨Á¤À½¼º ¹× ¾ó±¼ Ç¥Á¤ µ¥ÀÌÅͺ£À̽º
¿µ¹®Á¦¸ñ(English Title) Korean Emotional Speech and Facial Expression Database for Emotional Audio-Visual Speech Generation
ÀúÀÚ(Author) ¹éÁö¿µ   ±è¼¼¶ó   À̼®ÇÊ   Jiyoung Baek   Sera Kim   Seokpil Lee  
¿ø¹®¼ö·Ïó(Citation) VOL 23 NO. 02 PP. 0071 ~ 0077 (2022. 04)
Çѱ۳»¿ë
(Korean Abstract)
º» ¿¬±¸¿¡¼­´Â À½¼º ÇÕ¼º ¸ðµ¨À» °¨Á¤¿¡ µû¶ó À½¼ºÀ» ÇÕ¼ºÇÏ´Â ¸ðµ¨·Î È®ÀåÇÏ°í °¨Á¤¿¡ µû¸¥ ¾ó±¼ Ç¥Á¤À» »ý¼ºÇϱâ À§ÇÑ µ¥ÀÌÅͺ£À̽º¸¦ ¼öÁýÇÑ´Ù. µ¥ÀÌÅͺ£À̽º´Â ³²¼º°ú ¿©¼ºÀÇ µ¥ÀÌÅÍ°¡ ±¸ºÐµÇ¸ç °¨Á¤ÀÌ ´ã±ä ¹ßÈ­¿Í ¾ó±¼ Ç¥Á¤À¸·Î ±¸¼ºµÇ¾î ÀÖ´Ù. ¼ºº°ÀÌ ´Ù¸¥ 2¸íÀÇ Àü¹® ¿¬±âÀÚ°¡ Çѱ¹¾î·Î ¹®ÀåÀ» ¹ßÀ½ÇÑ´Ù. °¢ ¹®ÀåÀº anger, happiness, neutrality, sadnessÀÇ 4°¡Áö °¨Á¤À¸·Î ±¸ºÐµÈ´Ù. °¢ ¿¬±âÀÚµéÀº ÇÑ °¡ÁöÀÇ °¨Á¤ ´ç ¾à 3300°³ÀÇ ¹®ÀåÀ» ¿¬±âÇÑ´Ù. À̸¦ ÃÔ¿µÇÏ¿© ¼öÁýÇÑ Àüü 26468°³ÀÇ ¹®ÀåÀº Áߺ¹µÇÁö ¾ÊÀ¸¸ç ÇØ´çÇÏ´Â °¨Á¤°ú À¯»çÇÑ ³»¿ëÀ» ´ã°í ÀÖ´Ù. ¾çÁúÀÇ µ¥ÀÌÅͺ£À̽º¸¦ ±¸ÃàÇÏ´Â °ÍÀÌ ÇâÈÄ ¿¬±¸ÀÇ ¼º´É¿¡ Áß¿äÇÑ ¿ªÇÒÀ» ÇϹǷΠµ¥ÀÌÅͺ£À̽º¸¦ °¨Á¤ÀÇ ¹üÁÖ, °­µµ, ÁøÁ¤¼ºÀÇ 3°¡Áö Ç׸ñ¿¡ ´ëÇØ Æò°¡ÇÑ´Ù. µ¥ÀÌÅÍÀÇ Á¾·ù¿¡ µû¸¥ Á¤È®µµ¸¦ ¾Ë¾Æº¸±â À§ÇØ ±¸ÃàµÈ µ¥ÀÌÅͺ£À̽º¸¦ À½¼º-¿µ»ó µ¥ÀÌÅÍ, À½¼º µ¥ÀÌÅÍ, ¿µ»ó µ¥ÀÌÅÍ·Î ³ª´©¾î Æò°¡¸¦ ÁøÇàÇÏ°í ºñ±³ÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
In this paper, a database is collected for extending the speech synthesis model to a model that synthesizes speech according to emotions and generating facial expressions. The database is divided into male and female data, and consists of emotional speech and facial expressions. Two professional actors of different genders speak sentences in Korean. Sentences are divided into four emotions: happiness, sadness, anger, and neutrality. Each actor plays about 3300 sentences per emotion. A total of 26468 sentences collected by filming this are not overlap and contain expression similar to the corresponding emotion. Since building a high-quality database is important for the performance of future research, the database is assessed on emotional category, intensity, and genuineness. In order to find out the accuracy according to the modality of data, the database is divided into audio-video data, audio data, and video data.
Å°¿öµå(Keyword) À½¼ºÇÕ¼º   °¨Á¤À½¼º   µ¥ÀÌÅͺ£À̽º   ¸ÖƼ¸ð´Þ   Speech Synthesis   Speech Emotion   database   Multi Modal  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå