MALSORI (대한음성학회지:말소리)
- Issue 66
- /
- Pages.61-72
- /
- 2008
- /
- 1226-1173(pISSN)
Performance Improvement of Classification Between Pathological and Normal Voice Using HOS Parameter
HOS 특징 벡터를 이용한 장애 음성 분류 성능의 향상
- Lee, Ji-Yeoun (ICU) ;
- Jeong, Sang-Bae (ICU) ;
- Choi, Hong-Shik ;
-
Hahn, Min-Soo
(ICU)
- 이지연 (한국정보통신대학교(ICU) 음성/음향 정보 연구실) ;
- 정상배 (한국정보통신대학교(ICU) 음성/음향 정보 연구실) ;
- 최흥식 (연세대학교 의과대학 영동세브란스병원 이비인후과) ;
-
한민수
(한국정보통신대학교(ICU) 음성/음향 정보 연구실)
- Published : 2008.06.30
Abstract
This paper proposes a method to improve pathological and normal voice classification performance by combining multiple features such as auditory-based and higher-order features. Their performances are measured by Gaussian mixture models (GMMs) and linear discriminant analysis (LDA). The combination of multiple features proposed by the frame-based LDA method is shown to be an effective method for pathological and normal voice classification, with a 87.0% classification rate. This is a noticeable improvement of 17.72% compared to the MFCC-based GMM algorithm in terms of error reduction.
Keywords
- Pathological voice detection;
- Gaussian mixture model;
- Linear discriminant analysis;
- Classification and regression tree