This paper introduces a fuzzy approach for classifying speech emotions in which a fuzzy inference system based on fuzzy associative memory (FAM-FIS) is used for recognizing speech emotions. Experiments on two databases of emotion speech Emo-DB in German and SAVEE in English, and feature of Mel-Frequency Cepstral Coefficients (MFCC) showed that the accuracy rates of the fuzzy inference system are better than that of Bayes and Support Vector Machine (SVM) on same kind of features and databases. Namely, with MFCC feature and 19 dimensions, Emo-DB is 74.31% and SAVEE is 97.29%.
FreemanJ. A.SkapuraD. M.Neural Networks: Algorithms, Applications and Programming Techniques, Addison Wesley Publishing Company, USA, (1991).
2.
KoskoB.Neural network and fuzzy systemsPrentice-Hall, International (1992).
3.
JangD.-S. and ChoiH.-I., Fuzzy Inference System based on Fuzzy Associative Memory, J. Intelligent and Fuzzy Systems5 (1997), 271–284, IOS Press.
4.
LeeJ., KimW., ChaJ., KimG. and ChoiH.-I., A new recurrent fuzzy associative memory for recognizing time-series patterns contained ambiguity,
LaganàA. et al. (Eds.): ICCSA 2004, LNCS 3043, pp. 17–24.
5.
Ton-ThatAn H. Cao NhanT. Hyung-IlChoi An Algorithm for Optimizing Membership Functions of Fuzzy Inference Systems based on Fuzzy Associative Memory, Journal of Intelligent and Fuzzy systems27(1) (2014) 273–285, IOS Press.
6.
CastellanoG., FanelliA.M.MencarC. Design of Transparent Mamdani Fuzzy Inference Systems, Frontiers in Artificial Intelligence and Applications105 (2003), 468–477, IOS Press.
7.
GuillaumeS., Designing Fuzzy. Inference Systems from Data: An Interpretability-Oriented Review, IEEE Trans. Fuzzy Syst9(3) (2001), 426–443.
8.
ZimmermannH.-J.Fuzzy Set Theory and Its Application, Kluwer Academic Publishers, the 4th edition, 2001, USA.
9.
HebbO.D.The Organization of Behavior, John Wiley & Sons Inc., Fifth printing, 1959USA.
10.
BussoC., LeeS. and NarayananS., Analysis of emotionally salient aspects of fundamental frequency for emotion detection, IEEE Trans. Audio Speech Lang. Process. 17 (2009), 582–596.
11.
VlasenkoB., SchullerB., WendemuthA. and RigollG., Combining frame and turn-level information for robust recognition of emotions within speech, Proc. INTERSPEECH (2007), 2225–2228.
12.
DavisS. B.MerrmelsteinP.Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Sentences, IEEE Trans. Acoust. Speech Signal Process28(4) (1980), 357–366.
13.
LiX.SPEech Feature Toolbox. (SPEFT) Design and Emotional Speech Feature Extraction, M.S. Thesis, May 2007Marquette University.
14.
StevensS.S. and VolkmanJ., The relation of pitch to frequency: A revised scale, American Journal of Psychology53 (1940), 329–353.
15.
HuangX., AceroA. and HonH., Spoken Language Processing: A guide to theory, algorithm, and system development, Prentice HallUSA (2001).
16.
CleminsP., TrawickiM.B.Adi,K. TauJ. and Johnson,M. T. Generalized Perceptual Features for Vocalization Analysis across Multiple Species, IEEE Int. Conf. Acoust. Speech Signal Process, ICASSP, May 2006, Toulouse, France1, 253–256.
HaqS. and JacksonP.J.B., Multimodal Emotion Recognition, In
Wang.W. (ed), Machine Audition: Principles, Algorithms and Systems, July 2010, IGI Global Press, ISBN 978-16152091994, chapter 17, 398–423.
