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 |
| |
Affiliation: | 1. Medical Engineering Department, Afeka Tel Aviv Academic College of Engineering, 38 Mivtza Kadesh St., Tel Aviv 6910717, Israel;2. Yazmonit Ltd., Eshtaol, Israel;3. Research & Development Division, Sheba Medical Center, Tel-Hashomer, Israel;4. School of Electrical and Information Engineering, University of the Witwatersrand, Johannesburg, South Africa;1. Department of Medical Engineering, Afeka Tel Aviv Academic College of Engineering, Tel Aviv, Israel;2. School of Electrical and Information Engineering, University of the Witwatersrand, Johannesburg, South Africa;3. IBM Research|Africa, South Africa Lab, Johannesburg, South Africa;4. Yazmonit Ltd., Eshtaol, Israel;5. Unit of Mathematics, Afeka Tel Aviv Academic College of Engineering, Tel Aviv, Israel |
| |
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. |
| |
Keywords: | |
本文献已被 ScienceDirect 等数据库收录! |
|