<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="6.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Roberto Barra-Chicote</style></author><author><style face="normal" font="default" size="100%">Fernando Fernandez</style></author><author><style face="normal" font="default" size="100%">Syaheerah L. Lutfi</style></author><author><style face="normal" font="default" size="100%">Juan Manuel Lucas</style></author><author><style face="normal" font="default" size="100%">Javier Macias-Guarasa</style></author><author><style face="normal" font="default" size="100%">Juan Manuel Montero</style></author><author><style face="normal" font="default" size="100%">San Segundo, Ruben</style></author><author><style face="normal" font="default" size="100%">Jose Manuel Pardo</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Acoustic Emotion Recognition using Dynamic Bayesian Networks and Multi-Space Distributions</style></title><secondary-title><style face="normal" font="default" size="100%">10th Annual Conference of the Internacional Speech Communication Association (INTERSPEECH 2009)</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">automatic emotion recognition</style></keyword><keyword><style  face="normal" font="default" size="100%">dynamic bayesian networks</style></keyword><keyword><style  face="normal" font="default" size="100%">emotion challenge</style></keyword><keyword><style  face="normal" font="default" size="100%">multi-space probability distribution</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2009</style></year><pub-dates><date><style  face="normal" font="default" size="100%">09/2009</style></date></pub-dates></dates><urls><related-urls><url><style face="normal" font="default" size="100%">https://geintra-uah.org/system/files/p46039.pdf</style></url></related-urls></urls><publisher><style face="normal" font="default" size="100%">Internacional Speech Communication Association</style></publisher><pub-location><style face="normal" font="default" size="100%">Brighton, U.K.</style></pub-location><pages><style face="normal" font="default" size="100%">336-339</style></pages><language><style face="normal" font="default" size="100%">English</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;In this paper we describe the acoustic emotion recognition&lt;br /&gt;
system built at the Speech Technology Group of the Universidad&lt;br /&gt;
Politecnica de Madrid (Spain) to participate in the INTERSPEECH&lt;br /&gt;
2009 Emotion Challenge. Our proposal is based on&lt;br /&gt;
the use of a Dynamic Bayesian Network (DBN) to deal with&lt;br /&gt;
the temporal modelling of the emotional speech information.&lt;br /&gt;
The selected features (MFCC, F0, Energy and their variants) are&lt;br /&gt;
modelled as different streams, and the F0 related ones are integrated&lt;br /&gt;
under a Multi Space Distribution (MSD) framework, to&lt;br /&gt;
properly model its dual nature (voiced/unvoiced). Experimental&lt;br /&gt;
evaluation on the challenge test set, show a 67.06% and 38.24%&lt;br /&gt;
of unweighted recall for the 2 and 5-classes tasks respectively.&lt;br /&gt;
In the 2-class case, we achieve similar results compared with&lt;br /&gt;
the baseline, with 8.5 times less features. In the 5-class case, we&lt;br /&gt;
achieve a statistically significant 6.5% relative improvement.&lt;/p&gt;</style></abstract></record></records></xml>