JICCE (Çѱ¹Á¤º¸Åë½ÅÇÐȸ)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
Parts-Based Feature Extraction of Spectrum of Speech Signal Using Non-Negative Matrix Factorization |
¿µ¹®Á¦¸ñ(English Title) |
Parts-Based Feature Extraction of Spectrum of Speech Signal Using Non-Negative Matrix Factorization |
ÀúÀÚ(Author) |
Jeong-Won Park
Chang-Keun Kim
Kwang-Seok Lee
Si-Young Koh
Kang-In Hur
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 01 NO. 04 PP. 0209 ~ 0212 (2003. 12) |
Çѱ۳»¿ë (Korean Abstract) |
|
¿µ¹®³»¿ë (English Abstract) |
In this paper, we proposed new speech feature parameter through parts-based feature extraction of speech spectrum using Non-Negative Matrix Factorization (NMF). NMF can effectively reduce dimension for multi-dimensional data through matrix factorization under the non-negativity constraints, and dimensionally reduced data should be presented parts-based features of input data. For speech feature extraction, we applied Mel-scaled filter bank outputs to inputs of NMF, than used outputs of NMF for inputs of speech recognizer. From recognition experiment result, we could confirm that proposed feature parameter is superior in recognition performance than mel frequency cepstral coefficient (MFCC) that is used generally.
|
Å°¿öµå(Keyword) |
Non-Negative Matrix Factorization
Parts-based Feature Extraction
Mel-scaled Filter Bank Output
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|