RESEARCH

HOME RESEARCH
Behavior Computing
Speech and Language
Interpreting ambiguous emotional expressions
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 ofconsistent prototypical emotion expression often does not exist outside ofa 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.
Figures
Valence and activation plots of angry and happy sentences.
Valence and activation plots of angry and happy sentences.
Publication Date
2009/09/10
Conference
International Conference on Affective Computing and Intelligent Interaction and Workshops (ACII)
2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops
DOI
10.1109/ACII.2009.5349500
Publisher
IEEE