Challenges in real-life emotion annotation and machine learning based detection Export

@article{Devillers:2005, abstract = {Since the early studies of human behavior, emotion has attracted the interest of researchers in many disciplines of Neurosciences and Psychology. More recently, it is a growing field of research in computer science and machine learning. We are exploring how the expression of emotion is perceived by listeners and how to represent and automatically detect a subject's emotional state in speech. In contrast with most previous studies, conducted on artificial data with archetypal emotions, this paper addresses some of the challenges faced when studying real-life non-basic emotions. We present a new annotation scheme allowing the annotation of emotion mixtures. Our studies of real-life spoken dialogs from two call center services reveal the presence of many blended emotions, dependent on the dialog context. Several classification methods (SVM, decision trees) are compared to identify relevant emotional states from prosodic, disfluency and lexical cues extracted from the real-life spoken human-human interactions.}, address = {Oxford, UK, UK}, author = {Devillers, Laurence and Vidrascu, Laurence and Lamel, Lori}, citeulike-article-id = {6053616}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1150556.1150562}, citeulike-linkout-1 = {http://dx.doi.org/10.1016/j.neunet.2005.03.007}, doi = {10.1016/j.neunet.2005.03.007}, issn = {0893-6080}, journal = {Neural Netw.}, keywords = {emotion, learning, machine, network, neural, speech, voice}, number = {4}, pages = {407--422}, posted-at = {2009-11-01 15:27:26}, priority = {2}, publisher = {Elsevier Science Ltd.}, title = {Challenges in real-life emotion annotation and machine learning based detection}, url = {http://dx.doi.org/10.1016/j.neunet.2005.03.007}, volume = {18}, year = {2005} }

TY - JOUR ID - Devillers:2005 L3 - citeulike-article-id:6053616 N2 - Since the early studies of human behavior, emotion has attracted the interest of researchers in many disciplines of Neurosciences and Psychology. More recently, it is a growing field of research in computer science and machine learning. We are exploring how the expression of emotion is perceived by listeners and how to represent and automatically detect a subject's emotional state in speech. In contrast with most previous studies, conducted on artificial data with archetypal emotions, this paper addresses some of the challenges faced when studying real-life non-basic emotions. We present a new annotation scheme allowing the annotation of emotion mixtures. Our studies of real-life spoken dialogs from two call center services reveal the presence of many blended emotions, dependent on the dialog context. Several classification methods (SVM, decision trees) are compared to identify relevant emotional states from prosodic, disfluency and lexical cues extracted from the real-life spoken human-human interactions. IS - 4 JF - Neural Netw. SN - 0893-6080 AD - Oxford, UK, UK EP - 422 TI - Challenges in real-life emotion annotation and machine learning based detection PB - Elsevier Science Ltd. VL - 18 SP - 407 KW - emotion KW - learning KW - machine KW - network KW - neural KW - speech KW - voice AU - Devillers, Laurence AU - Vidrascu, Laurence AU - Lamel, Lori PY - 2005/// UR - http://dx.doi.org/10.1016/j.neunet.2005.03.007 ER -