Analysis of Speech Emotions Using Dynamics of Prosodic Parameters

  • Hemanta Kumar Palo
  • Mihir N. MohantyEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1040)


In this paper, an attempt is made to explore the dynamics of speech prosody to characterize and classify emotional states in a speech signal. The local or fine variations describing the prosodic dynamics are combined with the static prosodic parameters for a possible enhancement in the emotional speech recognition (ESR) accuracy. The efficient vector quantization (VQ) clustering algorithm has been applied to compress the static and dynamic parameters before further processing in a radial basis neural network (RBFNN) platform. Results reveal an improvement in ESR accuracy of 86.05% by involving both static and dynamic prosodic features as compared to 84.92% accuracy when the combination of static prosodic feature simulated alone.


Speech emotion Speech prosody Feature extraction Radial basis function neural network Classification 


  1. 1.
    Palo, H.K., Mohanty, M.N.: Compartive analysis of neural networks for speech emotion recognition. Int. J. Eng. Technol. 7(4), 111–126 (2018)Google Scholar
  2. 2.
    Rao, K.S., Reddy, R., Maity, S., Koolagudi, S. G.: Characterization of emotions using the dynamics of prosodic features. In: Speech Prosody 2010-Fifth International Conference (2010)Google Scholar
  3. 3.
    Mannepalli, K., Maloji, S., Sastry, P.N., Danthala, S., Mannepalli, D.P.: Text independent emotion recognition for Telugu speech by using prosodic features. Int. J. Eng. Technol. 7(4), 111–126; 7(2), 594–596 (2018)CrossRefGoogle Scholar
  4. 4.
    Cao, H., Verma, R., Nenkova, A.: Speaker-sensitive emotion recognition via ranking: studies on acted and spontaneous speech. Comput. Speech Lang. 29(1), 186–202 (2015)CrossRefGoogle Scholar
  5. 5.
    Palo, H.K., Mohanty, M.N.: Modified-VQ features for speech emotion recognition. J. Appl. Sci. 16(9), 406–418 (2016)CrossRefGoogle Scholar
  6. 6.
    Ramakrishnan, S.: Recognition of emotion from speech: a review. In: Speech Enhancement, Modeling and Recognition-Algorithms and Applications. InTech (2012)Google Scholar
  7. 7.
    Mishra, A.N., Chandra, M., Biswas, A., Sharan, S.N.: Robust features for connected Hindi digits recognition. Int. J. Sign. Process. Image Process. Pattern Recogn. 4(2), 79–90 (2011)Google Scholar
  8. 8.
    Kwon, O.W., Chan, K., Hao, J., Lee, T-W.: Emotion recognition by speech signals. In: Interspeech (2003)Google Scholar
  9. 9.
    Palo, H.K., Chandra, M., Mohanty, M.N.: Recognition of human speech emotion using variants of Mel-Frequency cepstral coefficients. In: Advances in Systems, Control and Automation, pp. 491–498. Springer, Singapore (2018)Google Scholar
  10. 10.
    Jackson, P., Haq, S.: Surrey audio-visual expressed emotion (SAVEE) database, pp. 398–423. University of Surrey, Guildford, UK (2014)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Department of Electronics and Communication EngineeringITER, Siksha ‘O’ Anusandhan UniversityBhubaneswarIndia

Personalised recommendations