A Comparative Study of Different Weighting Schemes on KNN-Based Emotion Recognition in Mandarin Speech

Emotion is fundamental to human experience influencing cognition, perception and everyday tasks such as learning, communication and even rational decision-making. This aspect must be considered in human-computer interaction. In this paper, we compare four different weighting functions in weighted KNN-based classifiers to recognize five emotions, including anger, happiness, sadness, neutral and boredom, from Mandarin emotional speech. The classifiers studied include weighted KNN, weighted CAP, and weighted DKNN. To give a baseline performance measure, we also adopt traditional KNN classifier. The experimental results show that the used Fibonacci weighting function outperforms than others in all weighted classifiers. The highest accuracy achieves 81.4% with weighted D-KNN classifier.

[1]  Takeo Kanade,et al.  Recognizing lower face action units for facial expression analysis , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[2]  Gwen Littlewort,et al.  Machine learning methods for fully automatic recognition of facial expressions and facial actions , 2004, 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583).

[3]  George N. Votsis,et al.  Emotion recognition in human-computer interaction , 2001, IEEE Signal Process. Mag..

[4]  Maja Pantic,et al.  An expert system for multiple emotional classification of facial expressions , 1999, Proceedings 11th International Conference on Tools with Artificial Intelligence.

[5]  Michael J. Black,et al.  Tracking and recognizing rigid and non-rigid facial motions using local parametric models of image motion , 1995, Proceedings of IEEE International Conference on Computer Vision.

[6]  Yuan-Hao Chang,et al.  Emotion Recognition and Evaluation of Mandarin Speech Using Weighted D-KNN Classification , 2005, ROCLING/IJCLCLP.

[7]  Sahibsingh A. Dudani.  The Distance-Weighted k-Nearest-Neighbor Rule , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[8]  Alex Pentland,et al.  Coding, Analysis, Interpretation, and Recognition of Facial Expressions , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Yasue Mitsukura,et al.  Emotional speech classification with prosodic prameters by using neural networks , 2001, The Seventh Australian and New Zealand Intelligent Information Systems Conference, 2001.

[10]  C. Darwin.  The Expression of the Emotions in Man and Animals , .

[11]  L. Lamel,et al.  Emotion detection in task-oriented spoken dialogues , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[12]  Laurence Devillers,et al.  Prosodic cues for emotion characterization in real-life spoken dialogs , 2003, INTERSPEECH.

[13]  John J. Ohala,et al.  Ethological theory and the expression of emotion in the voice , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[14]  J. Russell.  Is there universal recognition of emotion from facial expression? A review of the cross-cultural studies. , 1994, Psychological bulletin.

[15]  Nicu Sebe,et al.  Authentic Facial Expression Analysis , 2004, FGR.

[16]  David Escudero Mancebo,et al.  Analysis of prosodic features towards modelling of emotional and pragmatic attributes of speech , 2005, Proces. del Leng. Natural.

[17]  Eva Hudlicka,et al.  To feel or not to feel: The role of affect in human-computer interaction , 2003, Int. J. Hum. Comput. Stud..

[18]  L.C. De Silva,et al.  Speech based emotion classification , 2001, Proceedings of IEEE Region 10 International Conference on Electrical and Electronic Technology. TENCON 2001 (Cat. No.01CH37239).

[19]  Daniel Neagu,et al.  Similarity-based classifier combination for decision making , 2005, 2005 IEEE International Conference on Systems, Man and Cybernetics.