Comparison between decision-level and feature-level fusion of acoustic and linguistic features for spontaneous emotion recognition

Santiago Planet, Ignasi Iriondo

Producció científica: Capítol de llibreContribució a congrés/conferènciaAvaluat per experts

26 Cites (Scopus)

Resum

Detection of affective states in speech could improve the way users interact with electronic devices. However the analysis of speech at the acoustic level could be not enough to determine the emotion of a user speaking in a realistic scenario. In this paper we analysed the spontaneous speech recordings of the FAU Aibo Corpus at the acoustic and linguistic levels to extract two sets of acoustic and linguistic features. The acoustic set was reduced by a greedy procedure selecting the most relevant features to optimize the learning stage. We experimented with three classification approaches: Naïve-Bayes, a support vector machine and a logistic model tree, and two fusion schemes: decision-level fusion, merging the hard-decisions of the acoustic and linguistic classifiers by means of a decision tree; and feature-level fusion, concatenating both sets of features before the learning stage. Despite the low performance achieved by the linguistic data, a dramatic improvement was achieved after its combination with the acoustic information, improving the results achieved by this second modality on its own. The results achieved by the classifiers using the parameters merged at feature level outperformed the classification results of the decision-level fusion scheme, despite the simplicity of the scheme.

Idioma originalAnglès
Títol de la publicacióProceedings of the 7th Iberian Conference on Information Systems and Technologies, CISTI 2012
Estat de la publicacióPublicada - 2012
Esdeveniment7th Iberian Conference on Information Systems and Technologies, CISTI 2012 - Madrid, Spain
Durada: 20 de juny 201223 de juny 2012

Sèrie de publicacions

NomIberian Conference on Information Systems and Technologies, CISTI
ISSN (imprès)2166-0727
ISSN (electrònic)2166-0735

Conferència

Conferència7th Iberian Conference on Information Systems and Technologies, CISTI 2012
País/TerritoriSpain
CiutatMadrid
Període20/06/1223/06/12

Fingerprint

Navegar pels temes de recerca de 'Comparison between decision-level and feature-level fusion of acoustic and linguistic features for spontaneous emotion recognition'. Junts formen un fingerprint únic.

Com citar-ho