Title :
Bimodal emotion recognition
Author :
De Silva, Liyanage C. ; Ng, Pei Chi
Author_Institution :
Dept. of Electr. Eng., Nat. Univ. of Singapore, Singapore
Abstract :
This paper describes the use of statistical techniques and hidden Markov models (HMM) in the recognition of emotions. The method aims to classify 6 basic emotions (anger, dislike, fear, happiness, sadness and surprise) from both facial expressions (video) and emotional speech (audio). The emotions of 2 human subjects were recorded and analyzed. The findings show that the audio and video information can be combined using a rule-based system to improve the recognition rate
Keywords :
face recognition; hidden Markov models; knowledge based systems; pattern classification; speech recognition; statistical analysis; HMM; audio; bimodal emotion recognition; classification; emotional speech; facial expressions; hidden Markov models; rule-based system; statistical techniques; video; Electrical capacitance tomography; Emotion recognition; Face recognition; Hidden Markov models; Humans; Image databases; Image sequences; Signal processing algorithms; Speech recognition; Statistics;
Conference_Titel :
Automatic Face and Gesture Recognition, 2000. Proceedings. Fourth IEEE International Conference on
Conference_Location :
Grenoble
Print_ISBN :
0-7695-0580-5
DOI :
10.1109/AFGR.2000.840655
