Paper Info
Title
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 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.
Year
DOI
Venue
2009
10.1109/ACII.2009.5349500
Amsterdam
Keywords
Field
DocType
emotion recognition,acoustic features,ambiguous emotional expressions,categorical hard labels,emotion classification,emotion expression,emotional content,emotional profiles,interaction dynamics,nonprototypical utterances
Social psychology,Dialog box,Mood,Communication,Categorical variable,Computer science,Emotion classification,Utterance,Emotional expression,Hidden Markov model,Personality
Conference
ISBN
Citations 
PageRank 
978-1-4244-4799-2
24
0.97
References 
Authors
19
7
Name
Order
Citations
PageRank
Emily Mower1106259.08
Angeliki Metallinou224516.39
Chi-Chun Lee365449.41
Abe Kazemzadeh495752.95
Carlos Busso5161693.04
Sungbok Lee6139484.13
Narayanan Shrikanth75558439.23