The recognition of emotions from speech using GentleBoost classifier: A comparison approach

Title

The recognition of emotions from speech using GentleBoost classifier: A comparison approach

 Author

Datcu, D.
Rothkrantz, L.J.M.

Faculty

Electrical Engineering, Mathematics and Computer Science

 Department

Intelligent Systems

 Date

2006-06-15

 Abstract

The recognition of the internal emotional state of one person plays an important role in several human-related fields. Among them, human-computer interaction has recently received special attention. The current research is aimed at the analysis of segmentation methods and of the performance of the GentleBoost classifier on emotion recognition from speech. The data set used for emotion analysis is Berlin - a database of German emotional speech. A second data set is DES – Danish Emotional Speech data set is used for comparison purposes. Our contribution for the research community consists in a novel extensive study on the efficiency of using distinct numbers of frames per speech utterance for emotion recognition. Eventually, a set of GentleBoost 'committees' with optimal classification rates is determined based on an exhaustive study on the generated classifiers and on different types of segmentation.

 Subject

emotion recognition
speech processing
GentleBoost
Human-Computer Interfaces

 To reference this document use:

http://resolver.tudelft.nl/uuid:83596e10-18ce-4596-9b4f-8eea22d32ab4

 Source

CompSysTech ’06: International Conference on Computer Systems and Technologies, Veliko Tarnovo, Bulgaria, 15-16 June 2006

 Part of collection

Institutional Repository

 Document type

conference paper

 Rights

(c) 2006 Datcu, D.
Rothkrantz, L.J.M.
Files
PDF 10.1.1.127.5644-libre1.pdf 102.63 KB
Close viewer