Detecting emotions and driver states in a broad sense (e.g. annoyance, anger, and fatigue) can help to enhance acceptance and comfort of these systems themselves as well as accident related safety. Adapting the system output, e.g., in speech interfaces of Driver Assistance Systems to the actual emotional and energetic driver states might enhance the acceptance of this empathic, emotional-intelligent communication due to its improved naturalism. In addition, comfort and comprehensiveness might be improved if the system's output is adapted to the driver's actual e.g. stress-impaired attentional and cognitive resources. Furthermore, the detection of distracted driver states (e.g. pain, anger, emotional intensive conversation) could be beneficial from the viewpoint of safety concerns. Using voice communication as an indicator of emotion would have the following advantages: obtaining speech data is non-obtrusive, free from sensor application, calibration efforts, and robust against climatic environmental conditions. Several validation studies analysing e.g. basic emotions, fatigue, stress are presented in this paper reaching recognition rates for 2-class problems of about 80-90 %. Finally, current limitations and future demands (as e.g. freely accessible speech databases) for an efficient progress in speech emotions recognition are discussed.
Speech emotion recognition - Measuring driver states from voice characteristics
Erkennung von sprachlichen Emotionen - Bestimmung des Fahrerzustands aus der Stimmlage
Der Mensch im Mittelpunkt technischer Systeme, Berliner Werkstatt Mensch-Maschine-Systeme, 8 ; 98-103
2009
6 Seiten, 1 Bild, 1 Tabelle, 23 Quellen
Aufsatz (Konferenz)
Datenträger
Englisch
Speech-Based Driver Emotion Recognition
TIBKAT | 2023
|Speech-Based Driver Emotion Recognition
Springer Verlag | 2022
|Driver emotion recognition method and recognition device
Europäisches Patentamt | 2024
|Europäisches Patentamt | 2021
|