Detecting anger in automated voice portal dialogs. Burkhardt, F.; Ajmera, J.; Englert, R; Stegmann, J; and Burleson, W In ICSLP 2006 - Interspeech 2006. Proceedings of the 9th International Conference on Spoken Language Processing. Pittsburgh, PA, USA. September 17-21, 2006.
Detecting anger in automated voice portal dialogs [pdf]Paper  abstract   bibtex   
Anger detection is a topic that is gaining more and more atten- tion with voice portal carriers, as it can be useful for quality measurement and emotion-aware dialog strategies. In the con- text of a prototype voice portal we describe methods to search for training data, report on the performance of the prosodic clas- sifier under real world conditions and explore the use of di- alog information for anger prediction. The results show that, although significantly worse than under laboratory conditions, anger detection still works well above chance level and can be used to enhance real world voice-portal usability.
@incollection{burkhardt_detecting_2006,
	Author = {Burkhardt, Felix and Ajmera, Jitendra and Englert, R and Stegmann, J and Burleson, W},
	Booktitle = {ICSLP 2006 - Interspeech 2006. Proceedings of the 9th International Conference on Spoken Language Processing},
	Date = {2006},
	Date-Modified = {2016-09-23 19:22:33 +0000},
	File = {Attachment:files/1700/Burkhardt et al. - 2006 - Detecting anger in automated voice portal dialogs.pdf:application/pdf},
	Keywords = {dialogue systems, speech technology},
	Publisher = {Pittsburgh, PA, USA. September 17-21, 2006},
	Title = {Detecting anger in automated voice portal dialogs},
	Url = {http://felix.syntheticspeech.de/publications/recognitionOfAnger.pdf},
	Abstract = {Anger detection is a topic that is gaining more and more atten- tion with voice portal carriers, as it can be useful for quality measurement and emotion-aware dialog strategies. In the con- text of a prototype voice portal we describe methods to search for training data, report on the performance of the prosodic clas- sifier under real world conditions and explore the use of di- alog information for anger prediction. The results show that, although significantly worse than under laboratory conditions, anger detection still works well above chance level and can be used to enhance real world voice-portal usability.},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://felix.syntheticspeech.de/publications/recognitionOfAnger.pdf}}
Downloads: 0