earticle

논문검색

An Improved Algorithm of Speech Emotion Recognition

초록

영어

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

저자정보

  • 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
  • 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

참고문헌

자료제공 : 네이버학술정보

    ※ 원문제공기관과의 협약기간이 종료되어 열람이 제한될 수 있습니다.

    0개의 논문이 장바구니에 담겼습니다.