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

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ÇÐȸÁö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ÇÐȸÁö > µ¥ÀÌÅͺ£À̽º ¿¬±¸È¸Áö(SIGDB)

µ¥ÀÌÅͺ£À̽º ¿¬±¸È¸Áö(SIGDB)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) Spark¿¡¼­ SVMÀ» ÀÌ¿ëÇÑ À½¼º ƽ Áõ»ó °¨Áö ½Ã½ºÅÛ °³¹ß
¿µ¹®Á¦¸ñ(English Title) Development of Detection System of Vocal tic Symptoms using SVM Algorithm in Spark
ÀúÀÚ(Author) ä¼ö¼º   ±èÀξƠ  À̱Ôö   Su-Seong Chai   InA Kim   Kyu-Chul Lee  
¿ø¹®¼ö·Ïó(Citation) VOL 32 NO. 03 PP. 0115 ~ 0127 (2016. 12)
Çѱ۳»¿ë
(Korean Abstract)
À½¼º ƽ Àå¾Ö´Â °©ÀÛ½º·´°í ºü¸£°Ô ƯÁ¤ ¼Ò¸®¸¦ ¹Ýº¹Çϴ ƽ Áõ»óÀ» °¡Áö´Â Àå¾ÖÀ̸ç, À½¼º ƽ Áõ»óÀÇ Á¶±â Ä¡·á ¹× °¨Áö¸¦ ÅëÇØ ¶Ñ·¿ ÁõÈıºÀ¸·ÎÀÇ ¹ßÀüÀ» ¸·¾Æ¾ß ÇÑ´Ù. º» ³í¹®¿¡¼­´Â ±â°èÇнÀ ±â¹ÝÀÇ À½¼ºÀÎ½Ä ±â¼úÀ» »ç¿ëÇÏ¿© ÀÚµ¿ÀûÀ¸·Î À½¼º ƽ Áõ»óÀ» °¨ÁöÇÏ´Â ½Ã½ºÅÛÀ» °³¹ßÇÑ´Ù. ȯÀÚ¿¡ µû¶ó ´Ù¾çÇÏ°í ºÒ±ÔÄ¢ÀûÀÎ À½¼ºÆ½ Áõ»óÀ» °¨ÁöÇϱâ À§ÇØ MFCC Ư¡ º¤ÅÍ °ªÀ» ÃßÃâÇÏ¿´°í, SVM ¾Ë°í¸®ÁòÀ» ÅëÇØ °¨Áö ¸ðµ¨À» »ý¼ºÇÏ¿´À¸¸ç, ½ÇÇè Æò°¡ °á°ú 93.07%ÀÇ Á¤¹Ðµµ¸¦ È®ÀÎÇÏ¿´´Ù. ¶ÇÇÑ °¨Áö ¸ðµ¨ »ý¼º °úÁ¤ ½Ã ¸¹Àº ½Ã°£ÀÌ ¼Ò¿äµÇ´Â °ÍÀ» °í·ÁÇÏ¿©, °¨Áö ¸ðµ¨ »ý¼º °úÁ¤¿¡¼­ ¹ß»ýÇÏ´Â Áö¿¬ ½Ã°£À» °¨¼Ò½ÃÅ°±â À§ÇØ º» ³í¹®¿¡¼­´Â ÀÎ ¸Þ¸ð¸® ºÐ»ê ó¸® ¿£ÁøÀÎ Spark¸¦ »ç¿ëÇÏ¿© °¨Áö ¸ðµ¨ »ý¼º ½Ã°£À» ¾à 4¹è°¡·® °¨¼Ò½ÃÄ×´Ù.
¿µ¹®³»¿ë
(English Abstract)
Vocal tic is the disorder which repeats suddenly and rapidly certain sounds. In this paper, we develop detection system of vocal tic symptoms using speech recognition based on machine learning. In order to detect a variety of irregular vocal tic symptoms depending on people, we extract MFCC feature vectors and train the detection model using SVM algorithm. We perform the evaluation of the recognition model and it shows a precision of 93.07%. However, the process of training the detection model takes a lot of time. In order to reduce the train time, we use Apache Spark which is the in-memory distributed engine. The experimental result of the spark based train time is found to indicate a faster rate compared to Non-spark based train time.
Å°¿öµå(Keyword) À½¼º ƽ(Vocal Tic)   MFCC(Mel Frequency Cepstral Coefficient)   À½¼º ÀνÄ(Speech Recognition)   SVM(Support Vector Machine)   ¾ÆÆÄÄ¡ ½ºÆÄÅ©(Apache Spark)   Vocal Tic   MFCC(Mel Frequency Cepstral Coefficient)   Speech Recognition   SVM(Support Vector Machine)   Apache Spark  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå