ECTI TRANSACTIONS ON COMPUTER INFORMATION TECHNOLOGYVolume 15, No. 01, Month APRIL, Year 2021, Pages 73 - 81
Bimodal emotion recognition using deep belief network
Apichart Jaratrotkamjorn, Anant Choksuriwong
Abstract Download PDFThe emotions are very important in human daily life. In order to make the machine can recognize the human emotional state, and it can intelligently respond to need for human, which are very important in human-computer interaction. The majority of existing work concentrate on the classification of six basic emotions only. In this research work propose the emotion recognition system through the multimodal approach, which integrated information from both facial and speech expressions. The database has eight basic emotions (neutral, calm, happy, sad, angry, fearful, disgust, and surprised). Emotions are classified using deep belief network method. The experiment results show that the performance of bimodal emotion recognition system, it has better improvement. The overall accuracy rate is 97.92%.
Human- Computer Interaction (HCI), Emotion recognition, Face Detection, Speech Detection, Feature level fusion, Deep Be- lief Network (DBN)