원문정보
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
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
참고문헌
자료제공 : 네이버학술정보