Reduced Feature Set for Emotion Based Spoken Utterances of Normal and Special Children Using Multivariate Analysis and Decision Trees


  • M. A. Siddiqui Department of Software Engineering, NED University of Engineering and Technology, Karachi, Pakistan
  • S. A. Ali Department of Computer Science & Information Technology, NED University of Engineering and Technology, Karachi, Pakistan
  • N. G. Haider Department of Software Engineering, NED University of Engineering and Technology, Karachi, Pakistan
Volume: 8 | Issue: 4 | Pages: 3228-3233 | August 2018 |


The current paper deals with the use of multivariate data analysis and decision tree methods in order to reduce the feature set for the normal and special children speech in four different emotions: anger, happiness, neutral and sadness. Ten features were extracted, by an algorithm implemented in a previous study to classify the speech emotions of normal and special children. In the current study, the best features are selected using multivariate analysis: principal component analysis (PCA), factor analysis and decision tree. Step by step PCA is applied to reduce the feature set according to the variables that are collinear. The obtained reduced feature sets are applicable to both normal and special children samples. Experimental results revealed that PCA yields the feature set comprising pitch, intensity, formant, LPCC and rate of acceleration. Factor analysis provides three feature sets out of which the feature set comprising of Rasta PLP, MFCC, ZCR, and intensity provides the best result. Decision tree yields a feature set comprising energy, pitch and LPCC.


speech emotions, PCA, factor analysis, decision tree, features


Download data is not yet available.


S. Ramakrishnan, “Recognition of Emotion from Speech: A Review”, in: Speech Enhancement, Modeling and Recognition- Algorithms and Applications, pp. 121-138, InTech, 2012 DOI:

S. Pahune, N. Mishra, “Emotion Recognition through Combination of Speech and Image Processing: A Review”, International Journal on Recent and Innovation Trends in Computing and Communication, Vol. 3, No. 2, pp. 134-137, 2015

B. Schuller, A. Batliner, D. Seppi, S.Steidl, T. Vogt, J. Wagner, L. Devillers, L. Vidrascu, N. Amir, L. Kessous, V. Aharonson, “The relevance of feature type for the automatic classification of emotional user states: low level descriptors and functional”, in: INTERSPEECH 2007, Antwerp, Belgium, pp. 2253-2256, August 27-31, 2007

B. Schuller, G. Rigoll, “Recognizing interest in conversational speech–comparing bag of frames and supra-segmental features”, INTERSPEECH, Brighton, UK, pp. 1999-2002, September 6-10, 2009

Y. Zhou, Y. Sun, L. Yang, Y. Yan, “Applying articulatory features to speech emotion recognition”, IEEE 9th International Conference on Research Challenges in Computer Science, Shanghai, China, December 28-29, 2009 DOI:

S. Alghowinem, R. Goecke, M. Wagner, J. Epps, G. Parker, M. Breakspear, “Characterizing Depressed Speech for Classification”, INTERSPEECH, Florence, Italy, pp. 2534-2538, August 25-29, 2013

K. M.Chung, D. Jung, “Validity and reliability of the Korean version of autism spectrum disorders comorbid for children (ASD-CC)”, Research in Autism Spectrum Disorders, Vol. 39, pp.1-10, 2017 DOI:

M. A. Siddiqui, N. G. Haider, S. A. Ali, S. Hina, “A: Novel Approach for Features Extraction towards Classifying Normal and Special Children Speech Emotions in Urdu Language”, International Journal of Computer Science and Network Security, Vol. 17, No. 7, pp. 188-195, 2017

L. E. Aik, L. C Kiang, Z. B. Mohamed, T. W Hong, “A review on the multivariate statistical methods for dimensional reduction studies”, in: AIP Conference Proceedings, Perlis, Malaysia, Vol. 1847, No. 1, AIP Publishing, 2017 DOI:

K. Morris, P. D. McNicholas, “Clustering, classification, discriminant analysis, and dimension reduction via generalized hyperbolic mixtures”, Computational Statistics and Data Analysis, Vol. 97, pp. 133-150, 2016 DOI:

Y. W. Lin, B. C Deng, Q. S Xu,Y. H. Yun, Y. Z. Liang, “The equivalence of partial least squares and principal component regression in the sufficient dimension reduction framework”, Chemometrics and Intelligent Laboratory Systems, Vol. 150, pp. 58-64, 2016 DOI:

K. Mallick, S. Bhattacharyya, “Uncorrelated Local Maximum Margin Criterion: An Efficient Dimensionality reduction Method for Text Classification”, Procedia Technology, Vol. 4, pp. 370-374, 2012 DOI:

Y. Jingjie, X. Wang, W. Gu, L. Ma, “Speech Emotion Recognition Based on Sparse Representation


How to Cite

M. A. Siddiqui, S. A. Ali, and N. G. Haider, “Reduced Feature Set for Emotion Based Spoken Utterances of Normal and Special Children Using Multivariate Analysis and Decision Trees”, Eng. Technol. Appl. Sci. Res., vol. 8, no. 4, pp. 3228–3233, Aug. 2018.


Abstract Views: 469
PDF Downloads: 276

Metrics Information
Bookmark and Share

Most read articles by the same author(s)