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

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.