Whodunnit - Searching for the Most Important Feature Types Signalling Emotion-Related User States in Speech

Batliner A, Steidl S, Schuller B, Seppi D, Vogt T, Wagner J, Devillers L, Vidrascu L, Aharonson V, Kessous L, Amir N (2011)

Publication Language: English

Publication Type: Journal article, Original article

Publication year: 2011

Journal

Computer Speech and Language Elsevier

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

Publisher: Elsevier

Book Volume: 25

Pages Range: 4-28

Journal Issue: 1

URI: http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Batliner10-WSF.pdf

DOI: 10.1016/j.csl.2009.12.003

Abstract

In this article, we describe and interpret a set of acoustic and linguistic features that characterise emotional/emotion-related user states { con ned 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 di erent 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 di erent feature and extraction types. We establish di erent measures of impact and discuss the mutual in uence of acoustics and linguistics.

Authors with CRIS profile

Anton Batliner Lehrstuhl für Informatik 14 (Bild- und Sprachverarbeitung) (LME) Stefan Steidl Lehrstuhl für Informatik 14 (Bild- und Sprachverarbeitung) (LME)

Involved external institutions

Technische Universität München (TUM) DE Germany (DE) Fondazione Bruno Kessler (FBK) (früher: ITC-irst) IT Italy (IT) Universität Augsburg DE Germany (DE) Computer Science Laboratory for Mechanics and Engineering Sciences / Laboratoire d'informatique pour la mécanique et les sciences de l'ingénieur (LIMSI-CNRS) FR France (FR) Tel Aviv University IL Israel (IL)

How to cite

APA:

Batliner, A., Steidl, S., Schuller, B., Seppi, D., Vogt, T., Wagner, J.,... Amir, N. (2011). Whodunnit - Searching for the Most Important Feature Types Signalling Emotion-Related User States in Speech. Computer Speech and Language, 25(1), 4-28. https://doi.org/10.1016/j.csl.2009.12.003

MLA:

Batliner, Anton, et al. "Whodunnit - Searching for the Most Important Feature Types Signalling Emotion-Related User States in Speech." Computer Speech and Language 25.1 (2011): 4-28.

BibTeX: Download