Advertisement

Mobile Networks and Applications

, Volume 23, Issue 4, pp 1097–1102 | Cite as

Detecting Human Emotions in a Large Size of Database by Using Ensemble Classification Model

  • Sathit Prasomphan
  • Surinee Doungwichain
Article
  • 49 Downloads

Abstract

One of the most challenging researches in the field of Human-Computer Interaction (HCI) is Speech Emotion Recognition (SER). Several factors affect to the classification result. For example, the accuracy of detecting emotion depends on type of emotion and number of emotion which is classified and quality of speech is also the importance feature. Four different emotion types (anger, happy, natural, and sad) from Thai speech was used in this research. All of theses speech were recorded from Thai drama show which were most similar with daily life speech. The ensemble classification method with majority weight voting was used. This proposed algorithms used the combination of Support Vector Machine, Neural Network and k-Nearest Neighbors for emotion classification. The experimental results show that emotion classification by using the ensemble classification method by using the majority weight voting can efficiency give the better accuracy results than the single model. The proposed method has better results when using with fundamental frequency (F0) and Mel-Frequency Cepstral Coefficients (MFCC) of speech which give the accuracy results at 70.69.

Keywords

Speech emotion recognition Feature extraction Ensemble classification Weight majority vote K-nearest neighbor Neural network Support vector machines 

Notes

Acknowledgements

This research was funded by King Mongkut’s University of Technology North Bangkok. Contract no. KMUTNB-58-GEN-048.

References

  1. 1.
    Ayadi MMHE, Kamel MS, Karray F (2011) Survey on speech emotion recognition: features, classification schemes, and databases. Pattern Recogn 44:572–587Google Scholar
  2. 2.
    Xu S, Liu Y, Liu X (2013) Speaker recognition and speech emotion recognition based on GMM. In: 3rd international conference on electric and electronicsGoogle Scholar
  3. 3.
    Seehapoch T, Wongthanavasu S (2011) Speech emotion recognition using Support Vector Machines. In: The 5th international conference on knowledge and smart technology (KST), pp 219–223Google Scholar
  4. 4.
    Stickel C, Ebner M, Steinbach-Nordmann S, Searle G, Holzinger A (2009) Emotion detection: application of the valence arousal space for rapid biological usability testing to enhance universal access in universal access in Human-Computer interaction addressing diversity. Lecture notes in computer science, LNCS 5614. Springer, Berlin, pp 615–624Google Scholar
  5. 5.
    Hong M, Jung JJ, Camacho D (2017) GRSAT: a novel method on group recommendation by social affinity and trustworthiness. Cybern Syst 48(3):140–161CrossRefGoogle Scholar
  6. 6.
    Burkhardt F, Paeschke A, Rolfes M, Sendlmeier W, Weiss B (2005) A database of German emotional speech. In: Proceedings of the interspeechGoogle Scholar
  7. 7.
    Kasuriya S, Teeramunkong T, Wutiwiwatchai C (2013) Developing a Thai emotional speech corpus. In: International conference on Asian spoken language research and evaluationGoogle Scholar
  8. 8.
    Kasuriya S, Banchaditt T, Somboon N, Teeramunkong T, Wutiwiwatchai C (2013) Detecting emotional speech in thai drama. In: 2nd ICT international student project conference (ICT-ISPC)Google Scholar
  9. 9.
    Thamsiri D, Meesad P (2011) Ensemble data classification based on decision tree, artificial neuron network and support vector machine optimized by genetic algorithm. J King's Mongkut's Univ Technol North Bangkok 21 (2):293–303Google Scholar
  10. 10.
    Hong M, Jung JJ, Piccialli F, Chianese A (2017) Social recommendation service for cultural heritage. Pers Ubiquit Comput 21(2):191–201CrossRefGoogle Scholar
  11. 11.
    Rieger SA Jr, Muraleedharan R, Ramachandran RP (2014) Speech based emotion recognition using spectral feature extraction and an ensemble of kNN classifiers. In: 9th international symposium on Chinese spoken language processing (ISCSLP), pp 589– 593Google Scholar
  12. 12.
    Anagnostopoulos T, Skourlas C (2014) Ensemble majority voting classifier for speech emotion recognition and prediction. J Syst Inf Technol 16(3):222–232CrossRefGoogle Scholar
  13. 13.
    Nicholson J, Takahashi K, Nakatsu R (1999) Emotion recognition in speech using neural networks. In: 6th international conference on neural information processing, vol 2, pp 495–501Google Scholar
  14. 14.
    Mu X, Lu J, Watta P, Hassoun MH (2009) Weighted voting-based ensemble classifiers with application to human face recognition and voice recognition. In: Proceedings of international joint conference on neural networks. Atlanta, Georgia, USA, pp 2168–2171Google Scholar
  15. 15.
    Bui KN, Jung JJ (2018) Internet of agents framework for connected vehicles: a case study on distributed traffic control system. J Parallel Distrib Comput 116:89–95CrossRefGoogle Scholar
  16. 16.
    Morrison D, Wang R, Silva LCD (2007) Ensemble methods for spoken emotion recognition in call-centres. J Speech Commun 49(2):98–112CrossRefGoogle Scholar
  17. 17.
    Aha D, Kibler D (1991) Instance-based learning algorithms. Mach Learn 6:37–66MATHGoogle Scholar
  18. 18.
    Sharkey AJC (1999) Combining artificial neural nets ensemble and modular multi-net systems. Springer, LondonCrossRefMATHGoogle Scholar
  19. 19.
    Vasuki P (2015) Speech emotion recognition using adaptive ensemble of class specific classifiers, research journal of applied sciences. Eng Technol 9(12):1105–1114Google Scholar
  20. 20.
    Sittidech P, Nai-arun N (2015) Bagging model with cost sensitive analysis on diabetes data. Inf Technol J, KMUTNB 11(1):82–90Google Scholar
  21. 21.
    Shen P, Changjun Z (2011) Automatic speech emotion recognition using support vector machine. In: International conference on electronic & mechanical engineering and information technology, pp 621–625Google Scholar
  22. 22.
    Orgaz GB, Jung JJ, Camacho D (2016) Social big data: recent achievements and new challenges. Inf Fusion 28:45–59CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Computer and Information Science, Faculty of Applied ScienceKing Mongkut’s University of Technology North BangkokBangkokThailand

Personalised recommendations