Pattern Recognition Methods and Features Selection for Speech Emotion Recognition System
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F15%3A86090758" target="_blank" >RIV/61989100:27240/15:86090758 - isvavai.cz</a>
Nalezeny alternativní kódy
RIV/61989100:27740/15:86090758
Výsledek na webu
<a href="http://www.hindawi.com/journals/tswj/2015/573068/" target="_blank" >http://www.hindawi.com/journals/tswj/2015/573068/</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1155/2015/573068" target="_blank" >10.1155/2015/573068</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Pattern Recognition Methods and Features Selection for Speech Emotion Recognition System
Popis výsledku v původním jazyce
The impact of the classification method and features selection for the speech emotion recognition accuracy is discussed in this paper. Selecting the correct parameters in combination with the classifier is an important part of reducing the complexity ofsystem computing. This step is necessary especially for systems that will be deployed in real-time applications. The reason for the development and improvement of speech emotion recognition systems is wide usability in nowadays automatic voice controlledsystems. Berlin database of emotional recordings was used in this experiment. Classification accuracy of artificial neural networks, k-nearest neighbours, and Gaussian mixture model is measured considering the selection of prosodic, spectral, and voicequality features. The purpose was to find an optimal combination of methods and group of features for stress detection in human speech. The research contribution lies in the design of the speech emotion recognition system due to its accur
Název v anglickém jazyce
Pattern Recognition Methods and Features Selection for Speech Emotion Recognition System
Popis výsledku anglicky
The impact of the classification method and features selection for the speech emotion recognition accuracy is discussed in this paper. Selecting the correct parameters in combination with the classifier is an important part of reducing the complexity ofsystem computing. This step is necessary especially for systems that will be deployed in real-time applications. The reason for the development and improvement of speech emotion recognition systems is wide usability in nowadays automatic voice controlledsystems. Berlin database of emotional recordings was used in this experiment. Classification accuracy of artificial neural networks, k-nearest neighbours, and Gaussian mixture model is measured considering the selection of prosodic, spectral, and voicequality features. The purpose was to find an optimal combination of methods and group of features for stress detection in human speech. The research contribution lies in the design of the speech emotion recognition system due to its accur
Klasifikace
Druh
J<sub>x</sub> - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)
CEP obor
IN - Informatika
OECD FORD obor
—
Návaznosti výsledku
Projekt
—
Návaznosti
S - Specificky vyzkum na vysokych skolach
Ostatní
Rok uplatnění
2015
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název periodika
The Scientific World Journal
ISSN
2356-6140
e-ISSN
—
Svazek periodika
2015
Číslo periodika v rámci svazku
Neuveden
Stát vydavatele periodika
US - Spojené státy americké
Počet stran výsledku
7
Strana od-do
1-7
Kód UT WoS článku
—
EID výsledku v databázi Scopus
2-s2.0-84939857445