Audio-Visual Affect Recognition Export

@article{citeulike:1296328, abstract = {The ability of a computer to detect and appropriately respond to changes in a user's affective state has significant implications to human-computer interaction (HCI). In this paper, we present our efforts toward audio-visual affect recognition on 11 affective states customized for HCI application (four cognitive/motivational and seven basic affective states) of 20 nonactor subjects. A smoothing method is proposed to reduce the detrimental influence of speech on facial expression recognition. The feature selection analysis shows that subjects are prone to use brow movement in face, pitch and energy in prosody to express their affects while speaking. For person-dependent recognition, we apply the voting method to combine the frame-based classification results from both audio and visual channels. The result shows 7.5\% improvement over the best unimodal performance. For person-independent test, we apply multistream HMM to combine the information from multiple component streams. This test shows 6.1\% improvement over the best component performance}, author = {Zeng, Zhihong and Tu, Jilin and Liu, Ming and Huang, Thomas S. and Pianfetti, Brian and Roth, Dan and Levinson, Stephen}, citeulike-article-id = {1296328}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/TMM.2006.886310}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4067013}, doi = {10.1109/TMM.2006.886310}, journal = {Multimedia, IEEE Transactions on}, keywords = {affect, audio, bimodal, hmm, naturalistic, recognition, video}, number = {2}, pages = {424--428}, posted-at = {2008-05-12 16:23:27}, priority = {3}, title = {Audio-Visual Affect Recognition}, url = {http://dx.doi.org/10.1109/TMM.2006.886310}, volume = {9}, year = {2007} }

TY - JOUR ID - citeulike:1296328 L3 - citeulike-article-id:1296328 N2 - The ability of a computer to detect and appropriately respond to changes in a user's affective state has significant implications to human-computer interaction (HCI). In this paper, we present our efforts toward audio-visual affect recognition on 11 affective states customized for HCI application (four cognitive/motivational and seven basic affective states) of 20 nonactor subjects. A smoothing method is proposed to reduce the detrimental influence of speech on facial expression recognition. The feature selection analysis shows that subjects are prone to use brow movement in face, pitch and energy in prosody to express their affects while speaking. For person-dependent recognition, we apply the voting method to combine the frame-based classification results from both audio and visual channels. The result shows 7.5% improvement over the best unimodal performance. For person-independent test, we apply multistream HMM to combine the information from multiple component streams. This test shows 6.1% improvement over the best component performance IS - 2 JF - Multimedia, IEEE Transactions on EP - 428 TI - Audio-Visual Affect Recognition VL - 9 SP - 424 KW - affect KW - audio KW - bimodal KW - hmm KW - naturalistic KW - recognition KW - video AU - Zeng, Zhihong AU - Tu, Jilin AU - Liu, Ming AU - Huang, Thomas AU - Pianfetti, Brian AU - Roth, Dan AU - Levinson, Stephen PY - 2007/// UR - http://dx.doi.org/10.1109/TMM.2006.886310 ER -