The traditional K-nearest neighbor algorithm existences of the risk of miscarriage of justice, for its shortage a speech emotion recognition algorithm based on fuzzy K-nearest neighbors is proposed. By introducing the fuzzy membership concept, different characteristic parameters for the different contribution of emotion recognition are calculated, and the weighted Euclidean distance is used in speech emotion recognition. The experimental results show the effectiveness of the algorithm.
목차
Abstract 1. Introduction 2. K-nearest Neighbor Classification Algorithm and Fuzzy Set Theory 2.1. K Nearest Neighbor Classification Algorithm 2.2. Fuzzy Set Theory 3. Fuzzy K Nearest Neighbor Classification Algorithm 4. Speech Emotion Recognition based on FKNN 4.1. Speech Emotion Feature Extraction 4.2. Speech Emotion Recognition based on Fuzzy K -nearest Neighbor 5. Experiment of Speech Emotion Recognition based on FKNN 5.1. Experimental Environment and Emotional Speech Database 5.2. Emotional Feature Extraction 5.3. Experimental Results and Analysis 6. Conclusion References
키워드
Speech emotion recognitionfuzzy class membership functionFKNN (fuzzy K-Nearest Neighbor)
저자
Shulan Xia [ College of Electrical Engineering, Yancheng Institute of Technology, Yancheng 224051, Jiangsu, PR China ]
Jilin Wang [ College of Information Engineering, Yancheng Institute of Technology, Yancheng 224051, Jiangsu, PR China ]
Corresponding author
Ru-gang Wang [ College of Information Engineering, Yancheng Institute of Technology, Yancheng 224051, Jiangsu, PR China ]
Li Zhao [ College of Information Science and Engineering, Southeast University, Nanjing 210096, Jiangsu, PR China ]
보안공학연구지원센터(IJUNESST) [Science & Engineering Research Support Center, Republic of Korea(IJUNESST)]
설립연도
2006
분야
공학>컴퓨터학
소개
1. 보안공학에 대한 각종 조사 및 연구
2. 보안공학에 대한 응용기술 연구 및 발표
3. 보안공학에 관한 각종 학술 발표회 및 전시회 개최
4. 보안공학 기술의 상호 협조 및 정보교환
5. 보안공학에 관한 표준화 사업 및 규격의 제정
6. 보안공학에 관한 산학연 협동의 증진
7. 국제적 학술 교류 및 기술 협력
8. 보안공학에 관한 논문지 발간
9. 기타 본 회 목적 달성에 필요한 사업
간행물
간행물명
International Journal of u- and e- Service, Science and Technology
간기
격월간
pISSN
2005-4246
수록기간
2008~2016
십진분류
KDC 505DDC 605
이 권호 내 다른 논문 / International Journal of u- and e- Service, Science and Technology Vol.8 No.12