• 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¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)

Çѱ¹Á¤º¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ÇǺ¸È£ÀÚ ¸ð´ÏÅ͸µ ½Ã½ºÅÛÀ» À§ÇÑ È¯°æÀ½ ±â¹Ý »óȲ ÀνÄ
¿µ¹®Á¦¸ñ(English Title) Context Recognition Using Environmental Sound for Client Monitoring System
ÀúÀÚ(Author) Áö½ÂÀº   Á¶ÁØ¿µ   ÀÌÃæ±Ù   ¿À½Ã¿ø   ±è¿ìÀÏ   Seung-Eun Ji   Jun-Yeong Jo   Chung-Keun Lee   Siwon Oh   Wooil Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 19 NO. 02 PP. 0343 ~ 0350 (2015. 02)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®¿¡¼­´Â ¸ð¹ÙÀÏ ±â¹ÝÀÇ ÇǺ¸È£ÀÚ ¸ð´ÏÅ͸µ ½Ã½ºÅÛ Àû¿ëÀ» À§ÇÑ È¯°æÀ½ ±â¹ÝÀÇ »óȲ ÀÎ½Ä ±â¼úÀ» ¼Ò°³ÇÑ´Ù. »óȲ ÀÎ½Ä ½ÇÇèÀ» À§ÇØ ÃÑ 7°¡ÁöÀÇ À½Çâ ȯ°æÀ¸·Î ³ª´©¾î ȯ°æÀ½À» ÃëµæÇÑ´Ù. ȯ°æÀ½ ÀÎ½Ä ¼º´É ºñ±³¸¦ À§ÇØ MFCC¿Í LPCC Ư¡ ÃßÃâ ±â¹ýÀ» ÀÌ¿ëÇÑ´Ù. Åë°èÀû ±â¹ÝÀÇ ÆÐÅÏÀÎ½Ä ±â¹ýÀ» Àû¿ëÇϱâ À§ÇØ GMM ¹× HMM À½Çâ ¸ðµ¨À» ±â¹ÝÀ¸·Î Àνı⸦ ¼³°èÇÑ´Ù. ÀÎ½Ä ½ÇÇè °á°ú¿¡¼­´Â LPCC Ư¡ ÃßÃâ ±â¹ýÀÌ MFCC ±â¹ý º¸´Ù ¿ì¼öÇÏ°í, À½Çâ ¸ðµ¨Àº HMMÀÌ GMM¿¡ ºñÇØ ³ôÀº ÀÎ½Ä ¼º´ÉÀ» ³ªÅ¸³½´Ù. LPCC Ư¡À» »ç¿ëÇÏ°í HMM ¸ðµ¨À» ä¿ëÇÔÀ¸·Î½á ÃÖ°í 96.03%ÀÇ ÀνķüÀ» ³ªÅ¸³½´Ù. ÀÌ¿Í °°Àº °á°ú´Â À½¼º¿¡ ºñÇÏ¿© ´Ù¾çÇÑ ÁÖÆļö ¼ººÐÀÌ Á¸ÀçÇϴ ȯ°æÀ½À» Ç¥ÇöÇϴµ¥ MFCC º¸´Ù´Â LPCC°¡ È¿°úÀûÀÓÀ» ³ªÅ¸³»¸ç, ½Ã°£¿¡ µû¶ó º¯Çϴ Ư¼ºÀ» °®´Â ȯ°æÀ½Àº GMM º¸´Ù HMMÀÌ È¿°úÀûÀÓÀ» ÀÔÁõÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
This paper presents a context recognition method using environmental sound signals, which is applied to a mobile-based client monitoring system. Seven acoustic contexts are defined and the corresponding environmental sound signals are obtained for the experiments. To evaluate the performance of the context recognition, MFCC and LPCC method are employed as feature extraction, and statistical pattern recognition method are used employing GMM and HMM as acoustic models, The experimental results show that LPCC and HMM are more effective at improving context recognition accuracy compared to MFCC and GMM respectively. The recognition system using LPCC and HMM obtains 96.03% in recognition accuracy. These results demonstrate that LPCC is effective to represent environmental sounds which contain more various frequency components compared to human speech. They also prove that HMM is more effective to model the time-varying environmental sounds compared to GMM.
Å°¿öµå(Keyword) ȯ°æÀ½   »óȲ ÀνĠ  LPCC   MFCC   GMM   HMM   Environmental sound   Context recognition   LPCC   MFCC   HMM   GMM  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå