Classifier Subset Selection for the Stacked Generalization Method Applied to Emotion Recognition in Speech

Sensors

Aitor Álvarez¹  Basilio Sierra²  Andoni Arruti²  Juan-Miguel López-Gil²  Nestor Garay-Vitoria² 

[1] Vicomtech-IK4. Human Speech and Language Technologies Department, Paseo Mikeletegi 57, Parque Científico y Tecnológico de Gipuzkoa, 20009 Donostia-San Sebastián, SpainUniversity of the Basque Country (UPV/EHU), Paseo de Manuel Lardizabal 1, 20018 Donostia-San Sebastián, Spain;

关键词: affective computing;    machine learning;    speech emotion recognition;   

DOI  :  10.3390/s16010021

来源: mdpi

【 摘 要 】

In this paper, a new supervised classification paradigm, called classifier subset selection for stacked generalization (CSS stacking), is presented to deal with speech emotion recognition. The new approach consists of an improvement of a bi-level multi-classifier system known as stacking generalization by means of an integration of an estimation of distribution algorithm (EDA) in the first layer to select the optimal subset from the standard base classifiers. The good performance of the proposed new paradigm was demonstrated over different configurations and datasets. First, several CSS stacking classifiers were constructed on the RekEmozio dataset, using some specific standard base classifiers and a total of 123 spectral, quality and prosodic features computed using in-house feature extraction algorithms. These initial CSS stacking classifiers were compared to other multi-classifier systems and the employed standard classifiers built on the same set of speech features. Then, new CSS stacking classifiers were built on RekEmozio using a different set of both acoustic parameters (extended version of the Geneva Minimalistic Acoustic Parameter Set (eGeMAPS)) and standard classifiers and employing the best meta-classifier of the initial experiments. The performance of these two CSS stacking classifiers was evaluated and compared. Finally, the new paradigm was tested on the well-known Berlin Emotional Speech database. We compared the performance of single, standard stacking and CSS stacking systems using the same parametrization of the second phase. All of the classifications were performed at the categorical level, including the six primary emotions plus the neutral one.

【 授权许可】

CC BY   
© 2015 by the authors; licensee MDPI, Basel, Switzerland.