Title :
Detecting real life anger
Author :
Burkhardt, Felix ; Polzehl, Tim ; Stegmann, Joachim ; Metze, Florian ; Huber, Richard
Author_Institution :
Deutsche Telekom Labs., Berlin
Abstract :
Acoustic anger detection in voice portals can help to enhance human computer interaction. A comprehensive voice portal data collection has been carried out and gives new insight on the nature of real life data. Manual labeling revealed a high percentage of non-classifiable data. Experiments with a statistical classifier indicate that, in contrast to pitch and energy related features, duration measures do not play an important role for this data while cepstral information does. Also in a direct comparison between Gaussian Mixture Models and Support Vector Machines the latter gave better results.
Keywords :
Gaussian processes; acoustic signal processing; cepstral analysis; emotion recognition; human computer interaction; speech recognition; statistical analysis; support vector machines; Gaussian mixture models; acoustic anger detection; cepstral information; human computer interaction; real life anger; statistical classifier; support vector machines; voice portal data collection; voice portals; Acoustic signal detection; Automatic speech recognition; Automation; Classification algorithms; Clustering algorithms; Laboratories; Linear discriminant analysis; Portals; Support vector machine classification; Support vector machines; classification; detection; emotion; speech;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on
Conference_Location :
Taipei
Print_ISBN :
978-1-4244-2353-8
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2009.4960695
