Studying Self- and Active-Training Methods for Multi-feature Set Emotion Recognition
Automatic emotion classification is a task that has been subject of study from very different approaches. Previous research proves that similar performance to humans can be achieved by adequate combination of modalities and features. Nevertheless, large amounts of training data seem necessary to reach a similar level of accurate automatic classification. The labelling of training, validation and test sets is generally a difficult and time consuming task that restricts the experiments. Therefore, in this work we aim at studying self and active training methods and their performance in the task of emotion classification from speech data to reduce annotation costs. The results are compared, using confusion matrices, with the human perception capabilities and supervised training experiments, yielding similar accuracies.
KeywordsHuman perception of emotion automatic emotion classification semi-supervised learning active learning emotion recognition from speech
Unable to display preview. Download preview PDF.
- 3.Druck, G., Mann, G., McCallum, A.: Learning from labeled features using generalized expectation criteria. In: Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2008, pp. 595–602. ACM, New York (2008)Google Scholar
- 5.Hermansky, H.: The modulation spectrum in automatic recognition of speech. In: Proceedings of IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 140–147. IEEE (1997)Google Scholar
- 10.Monteleoni.: Learning with Online Constraints: Shifting Concepts and Active Learning. PhD thesis, Massachusetts Institute of Technology (2006)Google Scholar
- 11.Rabiner, L.R.: Fundamentals of Speech Recognition. Prentice-Hall (1993)Google Scholar
- 12.Scherer, K.R., Johnstone, T., Klasmeyer, G.: Affective Science. In: Handbook of Affective Sciences - Vocal expression of emotion, ch. 23, pp. 433–456. Oxford University Press (2003)Google Scholar
- 13.Scherer, S.: Analyzing the User’s State in HCI: From Crisp Emotions to Conversational Dispositions. PhD thesis. Ulm University (2011)Google Scholar
- 14.Settles.: Curious Machines: Active Learning with Structured Instances. PhD thesis, University of Wisconsin Madison (2008)Google Scholar
- 15.Settles, B.: Active learning literature survey. Computer Sciences Technical Report 1648. University of Wisconsin–Madison (2009)Google Scholar
- 17.Tong.: Active Learning: Theory and Applications. PhD thesis. Stanford University (2001)Google Scholar
- 18.Wendt, B.: Analysen Emotionaler Prosodie, Hallesche Schriften zur Sprechwissenschaft und Phonetik, vol. 20. Peter Lang Internationaler Verlag der Wissenschaften (2007)Google Scholar
- 19.Wendt, B., Scheich, H.: The ”Magdeburger Prosodie Korpus” - a spoken language corpus for fMRI-studies. In: Speech Prosody SProSIG 2002, pp. 699–701 (2002)Google Scholar
- 20.Zhu, X.: Semi-supervised learning literature survey. Technical Report 1530, Computer Sciences. University of Wisconsin-Madison (2005)Google Scholar