Emergency call centre emotion detector

21/03/2011 Inderscience

A system for emergency call centres that can assess a caller's stress levels or emotional state, and hence the urgency of the call, could reduce the impact of any given crisis and improve the emergency response. A team in The Netherlands reports just such an automatic emotion-detecting system in this month's International Journal of Intelligent Defence Support Systems.

Iulia Lefter of Delft University of Technology, the Netherlands Defence Academy and TNO Defence, Security and Safety, and colleagues, explain how emergency call centres are commonly overwhelmed by the sheer number of calls, especially during disaster situations or other national emergencies. A system that could distinguish automatically between a seriously urgent call and a more mundane issue could reduce the burden considerably and allow calls to be prioritised more effectively.

"Stress   and   negative   emotions,   in   general,   have   a   strong   influence   on   voice characteristics," the researchers explain. "Because  speech  is  a  natural  means  of  communication,  we  can  utilise the  sound patterns of speech  to  detect  stress  and  (negative)  emotions  in  a non-intrusive way by monitoring the communication." Factors such as how quickly a person is talking, whether or not there are rises and falls in pitch and tone and breathing rate, all change when we are stressed and can be detected.

The team has now "trained" a computer algorithm that receives audio input from emergency calls to assess the emotive level of the callers' speech. Four different training techniques were used with recordings from actual emergencies of known outcome and the team says their error rates are as low as 4.2% for a database of call centre recordings used in the research. Optimisation of the algorithm using a larger training set and more robust statistical tools might improve that still further.

The researchers expect the system to have military applications in the first instance. However, it could be adapted to the civilian emergency services and perhaps other applications, such as criminal investigations.

Full bibliographic information

"Automatic stress detection in emergency (telephone) calls" in Int. J. Intelligent Defence Support Systems, 2011, 4, 148-168
Attached files
  • Call centre emotion detector
  • Credit: CORDELIA MOLLOY / SCIENCE PHOTO LIBRARY Caption: MODEL RELEASED. Road accident first aid. Woman using a mobile phone to call for emergency aid for the victim of a road traffic accident (RTA). She has already placed the injured man in the recovery position. This position is used for unconscious patients who are breathing and have a heartbeat, provided there is no obvious injury to the back or neck. The bent arm and leg prop the patient and his head in a stable position, keeping the airways clear and allowing fluids (like vomit and blood) to drain safely without choking him.