14:00   Recognition of Non-prototypical Emotion from Speech: The Final Frontier
Chair: Bjoern Schuller, Anton Batliner, Stefan Steidl, Dino Seppi
14:00
20 mins 		Interpreting Ambiguous Emotional Expressions
Emily Mower, Angeliki Metallinou, Chi-Chun Lee, Abe Kazemzadeh, Carlos Busso, Sungbok Lee, Shrikanth Narayanan
Abstract: Emotion expression is a complex process involving dependencies based on time, speaker, context, mood, personality, and culture. Emotion classification algorithms designed for real-world application must be able to interpret the emotional content of an utterance or dialog given the modulations resulting from these and other dependencies. Algorithmic development often rests on the assumption that the input emotions are uniformly recognized by a pool of evaluators. However, this style of consistent prototypical emotion expression often does not exist outside of a laboratory environment. This paper presents methods for interpreting the emotional content of non-prototypical utterances. These methods include modeling across multiple time-scales and modeling interaction dynamics between interlocutors. This paper recommends classifying emotions based on emotional profiles, or soft-labels, of emotion expression rather than relying on just raw acoustic features or categorical hard labels. Emotion expression is both interactive and dynamic. Consequently, to accurately recognize emotional content, these aspects must be incorporated during algorithmic design to improve classification performance.
14:20
10 mins 		Real-time vocal emotion recognition in artistic installations and interactive storytelling: Experiences and lessons learnt from CALLAS and IRIS
Thurid Vogt, Elisabeth André, Johannes Wagner, Steve Gilroy, Fred Charles, Marc Cavazza
Abstract: Most emotion recognition systems still rely exclusively on prototypical emotional vocal expressions that may be uniquely assigned to a particular class. In realistic applications, there is, however, no guarantee that emotions are expressed in a prototypical manner. In this paper, we report on challenges that arise when coping with non-prototypical emotions in the context of the CALLAS project and the IRIS network. CALLAS aims to develop interactive art installations that respond to the multimodal emotional input of performers and spectators in real-time. IRIS is concerned with the development of novel technologies for interactive storytelling. Both research initiatives represent an extreme case of non-prototypicality since neither the stimuli nor the emotional responses to stimuli may be considered as prototypical.
14:30
10 mins 		A Multiple Perception Model on Emotional Speech
Jianhua Tao, Ya Li, Shifeng Pan
Abstract: More and more efforts have been made for the research of emotional speech recently. Although we may, sometimes be able to make a definite perceptual decision on emotion state, emotion is actually a kind of cline in a large vector space. Different emotions can be thought of as zones along an emotional vector. To resolve the ambiguity of emotion perception, the authors make an array of perception experiments. Furthermore, the paper creates a statistical model to simulate emotion perception and finds that there is an underlying consistency in the patterns of responses. The results show important cues on how to do multiple perception of the emotional speech.
14:40
10 mins 		Emotion Detection in Dialog Systems: Applications, Strategies and Challenges
Felix Burkhardt, Markus van Ballegooy, Klaus-Peter Engelbrecht, Tim Polzehl, Joachim Stegmann
Abstract: Emotion plays an important role in human communication and therefore also human machine dialog systems can benefit from affective processing. We present in this paper an overview of our work from the past few years and discuss general considerations, potential applications and experiments that we did with the emotional classification of human machine dialogs. Anger in voice portals as well as problematic dialog situations can be detected to some degree, but the noise in real life data and the issue of unambiguous emotion definiition are still challenging. Also, a dialog system reacting emotionally might raise expectations with respect to its intellectual abilities that it can not fulfill.
14:50
10 mins 		The Hinterland of Emotions: Facing the Open-Microphone Challenge
Stefan Steidl, Björn Schuller, Anton Batliner, Dino Seppi
Abstract: We first depict the challenge to address all non-prototypical varieties of emotional states signalled in speech in an open microphone setting, i. e. using all data recorded. In the remainder of the article, we illustrate promising strategies, using the FAU Aibo Emotion Corpus, by showing different degrees of classification performance for different degrees of prototypicality, and by elaborating on the use of ROC curves, classification confidences, and the use of correlation-based analyses.
15:00
30mins		 Panel
Laurence Devillers, Felix Burkhardt, Jianhua Tao, Elisabeth André, Shrikanth Narayanan, Björn Schuller
15:30
20 mins		 Floor Discussion