A speaker Independent Approach for Emotion Recognition

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F08%3APU77095" target="_blank" >RIV/00216305:26220/08:PU77095 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

A speaker Independent Approach for Emotion Recognition

Original language description

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.

Czech name

Rozpoznání emocí nezávisle na mluvčím

Czech description

The paper proposes a speaker independent procedure for classifying vocal expressions of emotion. The procedure is based on the splitting up of the emotion recognition process into two steps. In the first step, a combination of selected acoustic featuresis used to classify six emotions through a Bayesian Gaussian Mixture Model classifier (GMM). The two emotions that obtain the highest likelihood scores are selected for further processing in order to discriminate between them. For this purpose, a uniqueset of high-level acoustic features was identified using the Sequential Floating Forward Selection (SFFS) algorithm, and a GMM was used to separate between each couple of emotion. The mean classification rate is 81% with an improvement of 5% with respectto the most recent results obtained on the same database (75%).

Type

J_x - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)

CEP classification

JA - Electronics and optoelectronics

OECD FORD branch

—

Project

<a href="/en/project/GA102%2F07%2F1303" target="_blank" >GA102/07/1303: Non-linear methods of speech enhancement</a><br>

Continuities

Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year

2008

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Tools with artificial inteligence

ISSN

1082-3409

e-ISSN

—

Volume of the periodical

2008

Issue of the periodical within the volume

1

Country of publishing house

US - UNITED STATES

Number of pages

5

Pages from-to

—

UT code for WoS article

—

EID of the result in the Scopus database

—