Real-Time Model for Automatic Vocal Emotion Recognition
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F08%3APU75434" target="_blank" >RIV/00216305:26220/08:PU75434 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Real-Time Model for Automatic Vocal Emotion Recognition
Original language description
this paper deals with the task of vocal emotion recognition in real-time. For this aim, we introduced a simple model in the simulink environment based on the usage of mel bank coefficients as features and the GMM as a classifier. We made a comparison ofperformance of several preprocessing methods: MFCC, PLP, PCBF and MELB to find out which feature gives best classification results for four considered emotions: anger, happiness, sadness and neutral. We also made a comparison between two kinds of classifiers: Bayesian classifier based on Gaussian mixture models and artificial feed forward back propagation neural network.
Czech name
Rozpoznání emočního stavu v reálném čase
Czech description
this paper deals with the task of vocal emotion recognition in real-time. For this aim, we introduced a simple model in the simulink environment based on the usage of mel bank coefficients as features and the GMM as a classifier. We made a comparison ofperformance of several preprocessing methods: MFCC, PLP, PCBF and MELB to find out which feature gives best classification results for four considered emotions: anger, happiness, sadness and neutral. We also made a comparison between two kinds of classifiers: Bayesian classifier based on Gaussian mixture models and artificial feed forward back propagation neural network.
Classification
Type
D - Article in proceedings
CEP classification
JA - Electronics and optoelectronics
OECD FORD branch
—
Result continuities
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)
Others
Publication year
2008
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of 31th International Conference on Telecommunications and Signal Processing - TSP 2008
ISBN
978-963-06-5487-6
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
—
Publisher name
Neuveden
Place of publication
Neuveden
Event location
Parádfürdő
Event date
Sep 3, 2008
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—