2005 Special Issue: Challenges in real-life emotion annotation and machine learning based detection

  • Authors:
  • Laurence Devillers;Laurence Vidrascu;Lori Lamel

  • Affiliations:
  • Department of Human-Machine Communication, LIMSI-CNRS, BP133, 91 403, Orsay Cedex, France;Department of Human-Machine Communication, LIMSI-CNRS, BP133, 91 403, Orsay Cedex, France;Department of Human-Machine Communication, LIMSI-CNRS, BP133, 91 403, Orsay Cedex, France

  • Venue:
  • Neural Networks - Special issue: Emotion and brain
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

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.