Recognition of Human Emotion from a Speech Signal Based on Plutchik's Model

• Autorzy: Kamińska D. , Pelikant A.
• Języki publikacji: EN

Abstrakty

EN

Machine recognition of human emotional states is an essential part in improving man-machine interaction. During expressive speech the voice conveys semantic message as well as the information about emotional state of the speaker. The pitch contour is one of the most significant properties of speech, which is affected by the emotional state. Therefore pitch features have been commonly used in systems for automatic emotion detection. In this work different intensities of emotions and their influence on pitch features have been studied. This understanding is important to develop such a system. Intensities of emotions are presented on Plutchik's cone-shaped 3D model. The k Nearest Neighbor algorithm has been used for classification. The classification has been divided into two parts. First, the primary emotion has been detected, then its intensity has been specified. The results show that the recognition accuracy of the system is over 50% for primary emotions, and over 70% for its intensities.

Słowa kluczowe

EN

emotion detection; Plutchik's wheel of emotion; speech signal

• Wydawca: Polish Academy of Sciences, Committee of Electronics and Telecommunication
• Czasopismo: International Journal of Electronics and Telecommunications
• Rocznik: 2012
• Tom: Vol. 58, No. 2
• Strony: 165--170
• Opis fizyczny: Bibliogr. 30 poz., tab., wykr.

Twórcy

autor

Kamińska D.

autor

Pelikant A.

• Institute of Mechatronics and Information Systems, Technical University of Łódź, Stefanowskiego 18/22, 90-924 Łódź, Poland,

Bibliografia

• [1] R. Plutchik, “The nature of emotion.” American Scientist, vol. 89, July-August 2001.
• [2] G. Iriea, T. Satou, A. Kojima, T. Yamasaki, and K. Aizawa, “Affective audio-visual words and latent topic driving model for realizing movie affective scene classification.” IEEE Transactions on Multimedia, vol. 12, October 2010.
• [3] Y. Miyakoshi and S. Kato, “Facial emotion detection considering partial occlusion of face using bayesian network.” 2011 IEEE Symposium on Computers and Informatics.
• [4] Z. Yang, “Multimodal datafusion for aggression detection in train compartments.” February 2006.
• [5] T. Kostoulas, T. Ganchev, and N. Fotakis, “Study on speaker-independent emotion recognition from speech on real-world data,” Verbal and Nonverbal Features of Human-Human and Human-Machine Interaction 2008.
• [6] M. Kotti, F. Patern'o, and C. Kotropoulos, “Speaker-independent negative emotion recognition,” 2010 2nd International Workshop on Cognitive Information Processing.
• [7] J. Cichosz and K. Ślot, “Low-dimensional feature space derivation for emotion recognition.” ICSES 2006.
• [8] M. Lugger and B. Yang, “The relevance of voice quality features in speaker independent emotion recognition,” Proc. ICASSP, 2007.
• [9] Z. Ciota, Metody przetwarzania sygnałów akustycznych w komputerowej analizie mowy, 2010, in Polish.
• [10] T. Polzehl, A. Schmitt, and F. Metze, “Approaching multi-lingual emotion recognition from speech - on language dependency of acoustic/prosodic features for anger recognition.”
• [11] N. Kamaruddin and A. Wahab, “Driver behavior analysis through speech emotion understanding.” Intelligent Vehicles Symposium, 2010.
• [12] R. Hidayati, I. Purnama, and M. Purnomo, “The extraction of acoustic features of infant cry for emotion detection based on pitch and formants.” Proc. Instrumentation, Communications, Information Technology, and Biomedical Engineering (ICICI-BME), November 2010.
• [13] E. Mower, M. Matarić, and S. Narayanan, “A framework for automatic human emotion classification using emotion profiles.” Audio, Speech, and Language Processing, vol. 19, July 2011.
• [14] L. Vidrascu and L. Devillers, “Detection of real-life emotions in call centers.” Proc. Eurospeech Lizbona, 2005.
• [15] K. Izdebski, Emotions in the Human Voice Volume I Foundations, 2007.
• [16] Y. Wang and L. Guan, “Recognizing human emotional state from audiovisual signals.” Proc. IEEE Transactions on multimedia, vol. 10, 2008.
• [17] Y. Yeqing and T. Tao, “An new speech recognition method based on prosodic analysis and svm in zhuang language,” Proc. 2011 International Conference on Mechatronic Science, Electric Engineering and Computer, 2011.
• [18] A. Janicki and M. Turkot, “Rozpoznawanie stanu emocjonalnego mówcy z wykorzystaniem maszyny wektorów wspierajcych svm,” Proc. KSTiT, 2008, in Polish.
• [19] A. Shaukat and K. Chen, “Emotional state recognition from speech via soft-competition on different acoustic representations.” Proc. Neural Networks (IJCNN), 2011.
• [20] A. Razak, R. Komiya, and M. Abidin, “Comparison between fuzzy and nn method for speech emotion recognition.” Proc. Information Technology and Applications, ICITA 2005.
• [21] T. Nwe, S. Foo, and L. D. Silva, “Detection of stress and emotion in speech using traditional and fft based log energy features.” Proc. ICICSFCM 2003.
• [22] K. Soltani and R. Ainon, “Speech emotion detection based on neural networks.” Proc. Signal Processing and Its Applications 2007.
• [23] M. Gaurav, “Performance analysis of spectral and prosodic features and their fusion for emotion recognition in speech.” Proc. Spoken Language Technology Workshop 2008.
• [24] http://www.exaudios.com/.
• [25] K. Scherer, R. Banse, and H. Wallbott, “Emotion inferences from vocal expression correlate across languages and cultures.” Journal of Cross-Cultural Psychology, vol. 32, January 2001.
• [26] T. Zieliński, Cyfrowe przetwarzanie sygnałów. Od teorii do zastosowań., October 2009., in Polish.
• [27] https://www.msu.edu/course/.
• [28] S. Narayanan, C. Busso, and S. Lee, “Analysis of emotionally salient aspects of fundamental frequency for emotion detection.” IEEE Transactions on audio, speech, and language processing, 2009.
• [29] C. Basztura, Komputerowe systemy diagnostyki akustycznej., Wydawnictwo Naukowe PWN Warszawa 1996, in Polish.
• [30] K. Ślot, Rozpoznawanie biometryczne., December 2010, in Polish.