Publication detail

A speaker Independent Approach for Emotion Recognition

ATASSI, H. ESPOSITO, A.

Original Title

A speaker Independent Approach for Emotion Recognition

Type

journal article in Web of Science

Language

English

Original Abstract

The paper deals with speaker independent vocal emotion recognition. A new approach called "six by two" based on the division of the emotion recognitionprocess into two steps is presented. In the first step of the approach, a combination of selected acoustic features is used to classify six emotions. In the second step, two emotions with the highest likelihood are chosen from the first step to separate among them, for this purpose, a unique set of high-level acoustic features were selected using SFFS algorithm, these features were used to separate between each couple of emotions. For classification purposes, a Bayesian GMM classifier was used.

Keywords

emotion, recognition, speech, GMM

Authors

ATASSI, H.; ESPOSITO, A.

RIV year

2008

Released

10. 11. 2008

Publisher

IEEE Comuter Society

Location

Los Alamitos, California, USA

ISBN

1082-3409

Periodical

Tools with artificial inteligence

Year of study

2008

Number

1

State

United States of America

Pages from

147

Pages to

152

Pages count

5

BibTex

@article{BUT46781,
  author="Hicham {Atassi} and Anna {Esposito}",
  title="A speaker Independent Approach for Emotion Recognition",
  journal="Tools with artificial inteligence",
  year="2008",
  volume="2008",
  number="1",
  pages="147--152",
  issn="1082-3409"
}