JICCE (한국정보통신학회)
Current Result Document :
| 한글제목(Korean Title) |
Parts-Based Feature Extraction of Spectrum of Speech Signal Using Non-Negative Matrix Factorization |
| 영문제목(English Title) |
Parts-Based Feature Extraction of Spectrum of Speech Signal Using Non-Negative Matrix Factorization |
| 저자(Author) |
Jeong-Won Park
Chang-Keun Kim
Kwang-Seok Lee
Si-Young Koh
Kang-In Hur
|
| 원문수록처(Citation) |
VOL 01 NO. 04 PP. 0209 ~ 0212 (2003. 12) |
한글내용
(Korean Abstract) |
|
영문내용
(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.
|
| 키워드(Keyword) |
Non-Negative Matrix Factorization
Parts-based Feature Extraction
Mel-scaled Filter Bank Output
|
| 파일첨부 |
PDF 다운로드
|
