<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="6.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Iulia Lefter</style></author><author><style face="normal" font="default" size="100%">L.J.M. Rothkrantz</style></author><author><style face="normal" font="default" size="100%">David. A. van Leeuwen</style></author><author><style face="normal" font="default" size="100%">Pascal Wiggers</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Automatic Stress Detection in Emergency (Telephone) Calls</style></title><secondary-title><style face="normal" font="default" size="100%">Int. J. of Intelligent Defence Support Systems</style></secondary-title></titles><dates><year><style  face="normal" font="default" size="100%">2011</style></year></dates><volume><style face="normal" font="default" size="100%">4</style></volume><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">The abundance of calls to emergency lines during crises is diﬃcult to handle by the limited number of operators. Detecting if the caller is experiencing some extreme emotions can be a solution for distinguishing the more urgent calls. Apart from these and there are several other applications that can beneﬁt from awareness of the emotional state of the speaker. This paper describes the design of a system for selecting the calls that appear to be urgent and based on emotion detection. The system is trained using a database of spontaneous emotional speech from a call-centre. Four machine learning techniques are applied and based on either prosodic or spectral features and resulting in individual detectors. As a last stage and we investigate the eﬀect of fusing these detectors into a single detection system. We observe an improvement in the Equal Error Rate (eer) from 19.0 % on average for 4 individual detectors to 4.2 % when fused using linear logistic regression. All experiments are performed in a speaker independent cross-validation framework.</style></abstract><issue><style face="normal" font="default" size="100%">2</style></issue><section><style face="normal" font="default" size="100%">148-168</style></section></record></records></xml>