Speech Features Analysis for Tone Language Speaker Discrimination Systems

  • Mercy Edoho
  • Moses EkpenyongEmail author
  • Udoinyang Inyang
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 738)


In this paper, a speech pattern analysis framework for tone language speaker discrimination systems is proposed. We hold the hypothesis that speech feature variability is an efficient means for discriminating speakers. To achieve this, we exploit prosody-related acoustic features (pitch, intensity and glottal pulse) of corpus recordings obtained from male and female speakers of varying age categories: children (0–15), youths (16–30), adults (31–50), seniors (above 50)—and captured under suboptimal conditions. The speaker dataset was segmented into three sets: train, validation and test set—in the ratio of 70%, 15% and 15%, respectively. A 41 × 14 self-organizing map (SOM) architecture was then used to model the speech features, thereby determining the relationship between the speech features, segments and patterns. Results of a speech pattern analysis indicated wide F0 variability amongst children speakers compared with other speakers. This gap however closes as the speaker ages. Further, the intensity variability among speakers was similar across all speaker classes/categories, while glottal pulse exhibited significant variation among the different speaker classes. Results of SOM feature visualization confirmed high inter-variability—between speakers, and low intra-variability—within speakers.


Feature extraction Pattern analysis Self-organizing map Speaker variability 


  1. 1.
    W. Koenig, A new frequency scale for acoustic measurements. Bell Telephone Lab. Rec. 27, 299–301 (1949)Google Scholar
  2. 2.
    S.B. Davis, P. Ermelstein, Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust. Speech Sig. Process. 28(4), 357–366 (1980)CrossRefGoogle Scholar
  3. 3.
    N. Kaiki, K. Takeda, Y. Sagisaka, Linguistic properties in the control of segmental duration for speech synthesis, in Talking Machines: Theories, Models, and Designs, ed. By G. Bailly, C. Benoit, T.R. Sawalis (Elsevier, Amsterdam, 1992), pp. 255–263Google Scholar
  4. 4.
    M. Riley, Tree-based modelling of segmental duration, in Talking Machines: Theories, Models, and Designs, ed. By G. Bailly, C. Benoit, T.R. Sawallis (Elsevier Science, Amsterdam, 1992), pp. 265–273Google Scholar
  5. 5.
    N. Iwahashi, Y. Sagisaka, Duration modeling with multiple split regression, in Proceedings of the EUROSPEEC, 1993, pp. 329–332Google Scholar
  6. 6.
    J.P.H. van Santen, C. Shih, B. Mobius, E. Tzoukermann, M. Tanenblatt, Multi-lingual duration modeling, in Proceedings of the EUROSPEEC-97 vol. 5, 1997, pp. 2651–2654 Google Scholar
  7. 7.
    T. Yoshimura, K. Tokuda, T. Masuko, T Kobayashi, T Kitamura, Duration modeling for HMM-based speech synthesis, in Proceedings of the ICSLP 98, 1998, pp. 29–31Google Scholar
  8. 8.
    K.S. Rao, B. Yegnanarayana, Modeling durations of syllables using neural networks. Comput. Speech Lang. 1, 282–295 (2007)CrossRefGoogle Scholar
  9. 9.
    T. Shreekantha, V. Udayashankarab, M. Chandrika, Duration modelling using neural networks for hindi TTS system considering position of syllable in a word. Procedia Comput. Sci. 46, 60–67 (2015) CrossRefGoogle Scholar
  10. 10.
    A.K. Jain, A. Ross, S. Prabhakar, An introduction to biometric recognition. IEEE Trans. Circuit. Syst. Video Technol. 14(1), 4–20 (2004)CrossRefGoogle Scholar
  11. 11.
    U. Bhattacharjee, K. Sarmah, Speaker verification using acoustic and prosodic features. Adv. Comput. Int. J. 4(1), 45–51 (2013)CrossRefGoogle Scholar
  12. 12.
    S. Gabrielsson, S. Gabrielsson. The use of Self-Organizing Maps in Recommender Systems. A Survey of the Recommender Systems Field and a Presentation of a State of the Art Highly Interactive Visual Movie Recommender System. M.Sc. Thesis, Uppsala Universitet, Sweden, 2006Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Mercy Edoho
    • 1
  • Moses Ekpenyong
    • 1
    Email author
  • Udoinyang Inyang
    • 1
  1. 1.Department of Computer ScienceUniversity of UyoUyoNigeria

Personalised recommendations