• 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) Glottal flow ½ÅÈ£¿¡¼­ÀÇ Çâ»óµÈ Ư¡ÃßÃâ ¹× ´ÙÁß Æ¯Â¡ÆĶó¹ÌÅÍ °áÇÕÀ» ÅëÇÑ È­ÀÚÀÎ½Ä ¼º´É Çâ»ó
¿µ¹®Á¦¸ñ(English Title) Performance Improvement of Speaker Recognition Using Enhanced Feature Extraction in Glottal Flow Signals and Multiple Feature Parameter Combination
ÀúÀÚ(Author) °­ÁöÈÆ   ±è¿µÀÏ   Á¤»ó¹è   Jihoon Kang   Youngil Kim   Sangbae Jeong  
¿ø¹®¼ö·Ïó(Citation) VOL 19 NO. 12 PP. 2792 ~ 2799 (2015. 12)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®¿¡¼­´Â È­ÀÚ ÀνÄÀÇ ¼º´ÉÀ» °³¼±Çϱâ À§Çؼ­ glottal flow·ÎºÎÅÍ source mel-frequency cepstral coefficient (SMFCC), ¿Öµµ, ÷µµ¸¦ ÃßÃâÇÏ¿© È°¿ëÇÏ¿´´Ù. ÀϹÝÀûÀ¸·Î glottal flowÀÇ °íÁÖÆÄ ´ë¿ªÀº ÀÀ´äÀÇ Å©±â°¡ ÆòźÇϹǷΠ¹Ì¸® Á¤ÇÑ Â÷´ÜÁÖÆļö ¹Ì¸¸¿¡ ´ëÇؼ­¸¸ SMFCC¸¦ ÃßÃâÇÑ´Ù. ÃßÃâµÈ SMFCC, ¿Öµµ, ÷µµ´Â Á¾·¡ÀÇ Æ¯Â¡ ÆĶó¹ÌÅÍ¿Í °áÇÕµÈ ÈÄ Á¾·¡ÀÇ È­ÀÚÀÎ½Ä ½Ã½ºÅÛ°ú µ¿µîÇÑ Á¶°Ç¿¡¼­ÀÇ ¼º´É ºñ±³¸¦ À§ÇÏ¿© principal component analysis (PCA) ¹× linear discriminiat analysis (LDA)¸¦ ÅëÇÑ Â÷¿øÃà¼Ò°¡ ÇàÇØÁø´Ù. ´ë¿ë·®ÀÇ È­ÀÚÀÎ½Ä ½ÇÇè°á°ú¸¦ ÅëÇؼ­ Á¦¾ÈµÈ ÀÎ½Ä ½Ã½ºÅÛÀÌ Á¾·¡ÀÇ È­ÀÚÀÎ½Ä ½Ã½ºÅÛ º¸´Ù ´õ ÁÁÀº ¼º´ÉÀ» ³ªÅ¸³¿À» È®ÀÎÇÒ ¼ö ÀÖ¾úÀ¸¸ç, ƯÈ÷ °¡¿ì½Ã¾È È¥ÇÕÀÌ ³·À» ¶§ ´õ ³ôÀº ¼º´ÉÇâ»óÀ» ³ªÅ¸³»¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
In this paper, we utilize source mel-frequency cepstral coefficients (SMFCCs), skewness, and kurtosis extracted in glottal flow signals to improve speaker recognition performance. Generally, because the high band magnitude response of glottal flow signals is somewhat flat, the SMFCCs are extracted using the response below the predefined cutoff frequency. The extracted SMFCC, skewness, and kurtosis are concatenated with conventional feature parameters. Then, dimensional reduction by the principal component analysis (PCA) and the linear discriminat analysis (LDA) is followed to compare performances with conventional systems under equivalent conditions. The proposed recognition system outperformed the conventional system for large scale speaker recognition experiments. Especially, the performance improvement was more noticeable for small Gaussan mixtures.
Å°¿öµå(Keyword) È­ÀÚÀνĠ  ¼º¹®ÆÄ   ¿Öµµ   ÷µµ   ÁÖ¼ººÐ ºÐ¼®   ÁÖ¿äÀÎ ºÐ¼®   speaker recognition   glottal flow   skewness   kurtosis   PCA   LDA  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå