Whodunnit - Searching for the most important feature types signalling emotion-related user states in speech

  • Authors:
  • Anton Batliner;Stefan Steidl;Björn Schuller;Dino Seppi;Thurid Vogt;Johannes Wagner;Laurence Devillers;Laurence Vidrascu;Vered Aharonson;Loic Kessous;Noam Amir

  • Affiliations:
  • FAU: Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany;FAU: Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany;TUM: Institute for Human-Machine Communication, Technische Universität München, Germany;FBK: Fondazione Bruno Kessler - IRST, Trento, Italy;UA: Multimedia Concepts and their Applications, University of Augsburg, Germany;UA: Multimedia Concepts and their Applications, University of Augsburg, Germany;LIMSI-CNRS, Spoken Language Processing Group, Orsay Cedex, France;LIMSI-CNRS, Spoken Language Processing Group, Orsay Cedex, France;AFEKA: Tel Aviv Academic College of Engineering, Tel Aviv, Israel;TAU: Dep. of Communication Disorders, Sackler Faculty of Medicine, Tel Aviv University, Israel;TAU: Dep. of Communication Disorders, Sackler Faculty of Medicine, Tel Aviv University, Israel

  • Venue:
  • Computer Speech and Language
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this article, we describe and interpret a set of acoustic and linguistic features that characterise emotional/emotion-related user states - confined to the one database processed: four classes in a German corpus of children interacting with a pet robot. To this end, we collected a very large feature vector consisting of more than 4000 features extracted at different sites. We performed extensive feature selection (Sequential Forward Floating Search) for seven acoustic and four linguistic types of features, ending up in a small number of 'most important' features which we try to interpret by discussing the impact of different feature and extraction types. We establish different measures of impact and discuss the mutual influence of acoustics and linguistics.