Emotion Recognition using Linear Transformations in Combination with Video

The paper discuses the usage of linear transformations of Hid-den Markov Models, normally employed for speaker and envi-ronment adaptation, as a way of extracting the emotional com-ponents from the speech. A constrained version of Maximum Likelihood Linear Regression (CMLLR) transformation is used as a feature for classification of normal or aroused emotional state. We present a procedure of incrementally building a set of speaker independent acoustic models, that are used to esti-mate the CMLLR transformations for emotion classification. An audio-video database of spontaneous emotions (AvID) is briefly presented since it forms the basis for the evaluation of the proposed method. Emotion classification using the video part of the database is also described and the added value of combining the visual information with the audio features is shown. Index Terms: emotion recognition, emotional database, linear transformation