Comparison of Classifiers for Speech Emotion Recognition (SER) with Discriminative Spectral Features

  • Hemanta Kumar PaloEmail author
  • Debasis Behera
  • Bikash Chandra Rout
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 109)


This paper compares the classification ability of a few efficient classifiers in recognizing human speech emotions in terms of accuracy, computation time, and feature dimension. Both the static and dynamic mel-frequency cepstral coefficients (MFCC) are derived in the wavelet domain and are combined to form a suitable identification system model. Three popular neural network (NN) models such as the Gaussian mixture model (GMM), radial basis function network (RBFN), and the probabilistic neural network (PNN) have been put to test the reliability of these derived feature sets. The PNN classifier has shown to outperform both the RBFN and the GMM with low feature dimension, whereas the GMM shows an improved result for large feature dimensions. The combination of wavelet-based MFCCs and their dynamics remains more discriminative in classifying speech emotions as compared to either the MFCCs or wavelets acted alone.


Speech emotion recognition Spectral features Wavelet analysis Classifiers MFCC 


  1. 1.
    Mehrabian A (1971) Silent messages, vol 8. Wadsworth, Belmont, CAGoogle Scholar
  2. 2.
    Deng J, Frühholz S, Zhang Z, Schuller B (2017) Recognizing emotions from whispered speech based on acoustic feature transfer learning. IEEE Access 5:5235–5246Google Scholar
  3. 3.
    Joe CV, Sugi SSS (2016) Optimal feature for emotion recognition from speech. Afr J Basic Appl Sc 8(3):136–144Google Scholar
  4. 4.
    Sato N, Obuchi Y (2007) Emotion recognition using Mel-frequency Cepstral coefficients. Inf Media Technol 2(3):835–848Google Scholar
  5. 5.
    Palo HK, Chandra M, Mohanty MN (2018) Recognition of human speech emotion using variants of Mel-Frequency Cepstral coefficients. In: Advances in systems, control and automation. Springer, Singapore, pp 491–498Google Scholar
  6. 6.
    Palo HK, Mohanty MN (2018) Wavelet-based feature combination for recognition of emotions. Ain Shams Engg J 9:1799–1806CrossRefGoogle Scholar
  7. 7.
    Bishop CM (1995) Neural networks for pattern recognition. Oxford University PressGoogle Scholar
  8. 8.
    Javidi MM, Roshan EF (2013) Speech emotion recognition by using combinations of C5. 0, neural network (NN), and support vector machines (SVM) classification methods. J Math Comput Sc 6:191–200CrossRefGoogle Scholar
  9. 9.
    Specht DF, Missiles L, Inc S, Alto P (1990) Probabilistic neural networks and the polynomial Adaline as complementary techniques for classification. IEEE Tran Neural Net 1(1):111–121CrossRefGoogle Scholar
  10. 10.
    Palo HK, Sagar S (2018) Comparison of neural network models for speech emotion recognition. In: 2nd international conference of data science and business analytics, IEEE, pp 127–131Google Scholar
  11. 11.
    Ayadi E, Kamal MS, Karray F (2011) Survey on speech emotion recognition: features, classification schemes, and databases. Pattern Recogn 44(3):572–587 (Elsevier)CrossRefGoogle Scholar
  12. 12.
    Palo HK, Behera D, Analysis of speaker’s age using clustering approaches with emotionally dependent speech features. In: Critical approaches to information retrieval research, IGI Global, 2020, pp 172–197Google Scholar
  13. 13.
    Haq S, Jackson PJB (2010) Multimodal emotion recognition. In: Wang W (ed) Machine audition: principles, algorithms, and systems. IGI Global Press, chapter 17, pp 398–423Google Scholar
  14. 14.
    Palo HK, Chandra M, Mohanty MN (2017) Emotion recognition using MLP and GMM for Oriya language. Int J Comput Vision Robot 7(4):426–442CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Hemanta Kumar Palo
    • 1
    Email author
  • Debasis Behera
    • 2
  • Bikash Chandra Rout
    • 1
  1. 1.Siksha O Anusandhan (Deemed to Be University)BhubaneswarIndia
  2. 2.C. V. Raman College of EngineeringBhubaneswarIndia

Personalised recommendations