• 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) À¯»ö ÀâÀ½¿¡ ¿À¿°µÈ À½¼ºÀÇ Çâ»óÀ» À§ÇÑ ¹é»ö º¯È¯À» ÀÌ¿ëÇÑ ÀϹÝÈ­ ºÎ°ø°£ Á¢±Ù
¿µ¹®Á¦¸ñ(English Title) A Generalized Subspace Approach for Enhancing Speech Corrupted by Colored Noise Using Whitening Transformation
ÀúÀÚ(Author) ÀÌÁ¤¿í   ¼Õ°æ½Ä   ¹ÚÀå½Ä   ±èÇöÅ   Jeong-wook Lee   Kyung-sik Son   Jang-sik Park   Hyun-tae Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 15 NO. 08 PP. 1665 ~ 1674 (2011. 08)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®¿¡¼­´Â À¯»öÀâÀ½¿¡ ÀÇÇØ ¿À¿°µÈ À½¼º½ÅÈ£ÀÇ À½¼ºÇâ»ó ¾Ë°í¸®ÁòÀ» Á¦¾ÈÇÑ´Ù. À¯»öÀâÀ½°ú À½¼º½ÅÈ£°¡ ¼­·Î »ó°üÀÌ ¾øÀ» °æ¿ì À¯»öÀâÀ½Àº ¹é»öÈ­ º¯È¯À» ÅëÇØ ¹«»öÀâÀ½À¸·Î º¯È¯µÈ´Ù. ÀÌ º¯È¯µÈ ½ÅÈ£¸¦ À½¼º½ÅÈ£ Çâ»óÀ» À§ÇÑ ÀϹÝÈ­µÈ ºÎ°ø°£ Á¢±Ù¹ý¿¡ Àû¿ëÇÑ´Ù. Àüó¸® °úÁ¤¿¡¼­ÀÇ ¹é»öÈ­ º¯È¯À¸·Î ¹ß»ýµÇ´Â À½¼º ½ºÆåÆ®·³ ¿Ö°îÀº Á¦¾ÈÇÑ ¾Ë°í¸®ÁòÀÇ ÈÄ󸮸¦ ÅëÇØ ¿ª ¹é»öÈ­ÇÏ¿© º¹±¸ÇÑ´Ù. Á¦¾ÈÇÑ ¾Ë°í¸®ÁòÀÇ ¼º´ÉÀ» ÄÄÇ»ÅÍ ½Ã¹Ä·¹À̼ÇÀ¸·Î È®ÀÎÇÏ¿´´Ù. »ç¿ëÇÑ À¯»öÀâÀ½Àº ÀÚµ¿Â÷ ÀâÀ½°ú ¸ÖƼ ÅäÄ¿ ¹èºí ÀâÀ½ÀÌ´Ù. AURORA ¹× TIMIT µ¥ÀÌÅÍ º£À̽º¿¡¼­ ÃëµæÇÑ µ¥ÀÌÅÍ·Î ½ÇÇèÇßÀ» ¶§ Á¦¾ÈÇÏ´Â ¹æ¹ýÀÌ ½ÅÈ£´ëÀâÀ½ºñ ¹× ½ºÆåÆ®·³ ¿Ö°î Ãø¸é¿¡¼­ ±âÁ¸ Á¢±Ù¹ýº¸´Ù °³¼±µÊÀ» È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
In this paper, we proposed an algorithm for speech enhancement of speeches corrupted by colored noise. When there is no correlation between colored noise and speech signal, the colored noise turns into white noise through whitening transformation. This transformed signal has been applied to the generalized subspace approach for speech enhancement. The speech spectral distortion, produced by the whitening transformation as pre-processing, has been restored by using the inverse whitening transformation as post-processing of the proposed algorithm. The performance of the proposed algorithm for speech enhancement has been confirmed by computer simulation. The colored noises used in this experiment were car noise and multi-talker babble. It is confirmed that the proposed algorithm shows better performance from SNR and SSD viewpoint over the previous approach with the data from the AURORA and TIMIT data base.
Å°¿öµå(Keyword) À½¼º Çâ»ó   ÀϹÝÈ­ ºÎ°ø°£ Á¢±Ù   ¹é»ö º¯È¯   ÈÄ󸮠  Speech Enhancement   Generalized Subspace Approach   Whitening Transformation   Post-processing  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå