Proposing A Hybrid Approach for Emotion Classification using Audio and Video Data

摘要

Emotion recognition has been a research topic in the field of Human Computer Interaction(HCI) during recent years. Computers have become an inseparable part of human life. Usersneed human-like interaction to better communicate with computers. Many researchers havebecome interested in emotion recognition and classification using different sources. A hybridapproach of audio and text has been recently introduced. All such approaches have been done toraise the accuracy and appropriateness of emotion classification. In this study, a hybridapproach of audio and video has been applied for emotion recognition. The innovation of thisapproach is selecting the characteristics of audio and video and their features as a uniquespecification for classification. In this research, the SVM method has been used for classifyingthe data in the SAVEE database. The experimental results show the maximum classificationaccuracy for audio data is 91.63% while by applying the hybrid approach the accuracy achievedis 99.26%.