Emotional state recognition in customer service dialogues through telephone line

An automatic monitoring technique has been developed for the detection of the degree of the discontentment of the customer during a spontaneous conversation between the customer and the dispatcher through telephone. After the acoustic preprocessing clause sized segments were classified according to its emotional content, using support vector machine (SVM) classifier. A 15 sec long monitoring window was selected, and the clauses, which were automatically classified as “discontent” emotion, were counted in this window. Then, the window was moved forward, by 10 sec time steps. On the base of this monitoring technique it is possible to sign when the discontentment level has reached a critical “alarm level”.