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

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)

Á¤º¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ÆÄÇü Ư¡ ÃßÃâ°ú ½Å°æ¸Á ÇнÀ ±â¹Ý ¸ðÀ½ ¡®¤Ó¡¯ À½¼º ÀνÄ
¿µ¹®Á¦¸ñ(English Title) Speech Recognition for the Korean Vowel ¡®¤Ó¡¯ based on Waveform-feature Extraction and Neural-network Learning
ÀúÀÚ(Author) ³ë¿øºó   ÀÌÁ¾¿ì   ÀÌÀç¿ø   Wonbin Rho   Jongwoo Lee   Jaewon Lee  
¿ø¹®¼ö·Ïó(Citation) VOL 22 NO. 02 PP. 0069 ~ 0076 (2016. 02)
Çѱ۳»¿ë
(Korean Abstract)
ÃÖ±Ù ¸ðµç »ê¾÷¿¡¼­ »ç¹°ÀÎÅͳݿ¡ ´ëÇÑ °ü½ÉÀÌ ÁýÁߵǸ鼭 Áý, ȸ»ç, Â÷, ±æ°Å¸® µî Àΰ£ÀÌ »ýÈ°ÇÏ´Â ¸ðµç ȯ°æ¿¡ ÄÄÇ»Æà ±â¼úÀÌ Á¢¸ñµÇ°í ÀÖ´Ù. ÀÌ °°Àº »ç¹°ÀÎÅÍ³Ý È¯°æ¿¡¼­ À½¼ºÀνÄÀº Áß¿äÇÑ HCI ¼ö´ÜÀ¸·Î ÀÚ¸® Àâ°í ÀÖ´Ù. ÇöÁ¸ÇÏ´Â ¼­¹ö ±â¹ÝÀÇ À½¼ºÀνÄÀº ¼Óµµ°¡ ºü¸£°í ²Ï ³ôÀº ÀνķüÀ» º¸¿©ÁÖ°í´Â ÀÖÁö¸¸, µ¥ÀÌÅͺ£À̽º ³»¿¡ ÀúÀåµÇ¾î ÀÖ´Â ´Ü¾î ´ÜÀ§·Î ÀνÄÇϱ⠶§¹®¿¡ ÀÎÅÍ³Ý ¿¬°á°ú º¹ÀâÇÑ ÄÄÇ»ÆÃÀÌ ÇʼöÀûÀÌ´Ù. º» ³í¹®Àº Çѱ¹¾î À½¼Ò ¸ðÀ½ ¡®¤¿¡¯, ¡®¤Ã¡¯ ÀνĿ¡ ´ëÇÑ ÈÞ¸®½ºÆ½ ¾Ë°í¸®Áò¿¡ ÀÌÀº ¿¬±¸·Î ¸ðÀ½ ¡®¤Ó¡¯¿¡ ´ëÇÑ À½¼º ÀνÄÀ» ±¸ÇöÇÏ°íÀÚ ÇÑ´Ù. ¸ðÀ½ ¡®¤Ó¡¯ À½¼ºÀÇ ¿©·¯ ÆÄÇü ÆÐÅϵéÀ» °üÂûÇÑ °á°ú ¸ðÀ½ ¡®¤¿¡¯, ¡®¤Ã¡¯¿Í´Â ´Ù¸¥ ƯÁ¤ÇÑ ÆÄÇüÀÇ ÆÐÅÏÀ» °¡Áö°í ÀÖÀ½À» ¹ß°ßÇÏ¿´°í, ±× ÆÐÅÏÀ» ÀνÄÇÏ´Â ¾Ë°í¸®ÁòÀ» Á¦½ÃÇÑ´Ù. ¶ÇÇÑ, Á¦½ÃÇÑ ¾Ë°í¸®Áò¿¡ ½Å°æ¸Á ÇнÀÀ» Àû¿ëÇÏ¿© Àνļº°ø·üÀ» ³ôÀÌ´Â ½ÇÇè °á°úµµ Á¦½ÃÇÑ´Ù. ¸ðÀ½ ¡®¤Ó¡¯¿¡ ´ëÇÑ º» ¾Ë°í¸®ÁòÀº ÆÄÇüÀÇ Æ¯Â¡ÀûÀÎ ºÎºÐ ÃßÃâ ±â¹ÝÀ¸·Î ÀνÄÇϸç, ½Å°æ¸Á ÇнÀ±îÁö Àû¿ëÇÑ ÈÄ ½ÇÇèÇÑ °á°ú 90% ÀÌ»óÀÇ Á¤È®µµ·Î ¸ðÀ½ ¡®¤Ó¡¯¸¦ ÀνÄÇÏ´Â °ÍÀ» È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
With the recent increase of the interest in IoT in almost all areas of industry, computing technologies have been increasingly applied in human environments such as houses, buildings, cars, and streets; in these IoT environments, speech recognition is being widely accepted as a means of HCI. The existing server-based speech recognition techniques are typically fast and show quite high recognition rates; however, an internet connection is necessary, and complicated server computing is required because a voice is recognized by units of words that are stored in server databases. This paper, as a successive research results of speech recognition algorithms for the Korean phonemic vowel ¡®¤¿¡¯, ¡®¤Ã¡¯, suggests an implementation of speech recognition algorithms for the Korean phonemic vowel ¡®¤Ó¡¯. We observed that almost all of the vocal waveform patterns for ¡®¤Ó¡¯ are unique and different when compared with the patterns of the ¡®¤¿¡¯ and ¡®¤Ã¡¯ waveforms. In this paper we propose specific waveform patterns for the Korean vowel ¡®¤Ó¡¯ and the corresponding recognition algorithms. We also presents experiment results showing that, by adding neural-network learning to our algorithm, the voice recognition success rate for the vowel ¡®¤Ó¡¯ can be increased. As a result we observed that 90% or more of the vocal expressions of the vowel ¡®¤Ó¡¯ can be successfully recognized when our algorithms are used.
Å°¿öµå(Keyword) À½¼ºÀνĠ  ¸ðÀ½   ÆÄÇüƯ¡   ¡®¤Ó¡¯   ½Å°æ¸Á   Speech recognition   Vowel   Waveform feature   ¡®¤Ó¡¯   Neural network  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå