Title :
Emotion recognition from audiovisual information
Author :
Chen, L.S. ; Tao, H. ; Huang, T.S. ; Miyasato, T. ; Nakatsu, R.
Author_Institution :
Beckman Inst. for Adv. Sci. & Technol., Illinois Univ., Urbana, IL, USA
Abstract :
We report preliminary results on emotion recognition by machine from joint audiovisual input of facial video and speech. The results show potential advantages in using both modalities over either modality alone. The recognition rate for audio alone is about 75% and video alone about 70%. Using audiovisual data we achieved 97% without increasing the number of features. The improvement in performance is accredited to the complementary property between the two modalities. A possible application is in natural human-computer interfaces
Keywords :
audio-visual systems; computer interfaces; face recognition; sensor fusion; speech recognition; video signal processing; audiovisual information; audiovisual input; complementary property; emotion recognition; facial video; machine; natural human-computer interfaces; performance; recognition rate; speech input; Application software; Data mining; Emotion recognition; Face recognition; Feature extraction; Human computer interaction; Microwave integrated circuits; Performance analysis; Speech processing; Speech recognition;
Conference_Titel :
Multimedia Signal Processing, 1998 IEEE Second Workshop on
Conference_Location :
Redondo Beach, CA
Print_ISBN :
0-7803-4919-9
DOI :
10.1109/MMSP.1998.738917
