Machine Learning
Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Affective computing
Vocal communication of emotion: a review of research paradigms
Speech Communication - Special issue on speech and emotion
Fully generated scripted dialogue for embodied agents
Artificial Intelligence
A Study of Emotion Recognition and Its Applications
MDAI '07 Proceedings of the 4th international conference on Modeling Decisions for Artificial Intelligence
Affect and Emotion in Human-Computer Interaction: From Theory to Applications
Affect and Emotion in Human-Computer Interaction: From Theory to Applications
Affective Information Processing
Affective Information Processing
Multi-level Speech Emotion Recognition Based on HMM and ANN
CSIE '09 Proceedings of the 2009 WRI World Congress on Computer Science and Information Engineering - Volume 07
Image and Vision Computing
IEEE Transactions on Pattern Analysis and Machine Intelligence
A logic for reasoning about counterfactual emotions
Artificial Intelligence
ACII'05 Proceedings of the First international conference on Affective Computing and Intelligent Interaction
Speech emotional features extraction based on electroglottograph
Neural Computation
Hi-index | 0.00 |
To solve the speaker independent emotion recognition problem, a three-level speech emotion recognition model is proposed to classify six speech emotions, including sadness, anger, surprise, fear, happiness and disgust from coarse to fine. For each level, appropriate features are selected from 288 candidates by using Fisher rate which is also regarded as input parameter for Support Vector Machine (SVM). In order to evaluate the proposed system, principal component analysis (PCA) for dimension reduction and artificial neural network (ANN) for classification are adopted to design four comparative experiments, including Fisher+SVM, PCA+SVM, Fisher+ANN, PCA+ANN. The experimental results proved that Fisher is better than PCA for dimension reduction, and SVM is more expansible than ANN for speaker independent speech emotion recognition. The average recognition rates for each level are 86.5%, 68.5% and 50.2% respectively.