Phoneme Segmentation Technique Using Self-Organizing Map (SOM)

Part of the Studies in Computational Intelligence book series (SCI, volume 550)


This chapter provides a description of the proposed SOM-based segmentation technique and explains how it can be used to segment the initial phoneme from some CVC-type Assamese word. In Sect. 6.3, the SOM and PNN have been explained in a more relevant way, as they are used as parts of the technique. The work provides a comparison of the proposed SOM-based technique with the conventional DWT-based speech segmentation technique. Therefore, some experimental works are carried out to perform the DWT-based phoneme segmentation. The theoretical details of DWT-based technique are explained in Sect. 6.4. In Sect. 6.5, algorithms associated with the proposed segmentation technique are explained along with the experimental details. Result and discussions are included in the Sect. 6.6. Section 6.7 concludes the chapter.


CVC Segmentation SOM PNN DWT 


  1. 1.
    Grayden DB, Scordilis MS (1994) Phonemic segmentation of fluent speech. Proc IEEE Int Conf Acoust, Speech, Signal Process 1:73–76Google Scholar
  2. 2.
    Sweldens W, Deng B, Jawerth B, Peters G (1993) Wavelet probing for compression based segmentation. Proc SPIE 2034:266–276CrossRefGoogle Scholar
  3. 3.
    Wendt C, Petropulu AP (1996) Pitch determination and speech segmentation using the discrete wavelet transform. IEEE In Symp Circuits Syst Connect World 2:45–48Google Scholar
  4. 4.
    Zioko B, Manandhar S, Wilson RC (2006) Phoneme segmentation of speech. Proc 18th Int Conf Pattern Recogn 4:282–285Google Scholar
  5. 5.
    Paliwal KK, Kleijn WB (2003) Quantization of LPC parameters. J Inf Sci Eng 19:267–282Google Scholar
  6. 6.
    Kohonen T (1990) The self-organizing map. Proc IEEE 78(9):1464–1480CrossRefGoogle Scholar
  7. 7.
    Haykin S (2009) Neural network and learning machine, 3rd edn. PHI Learning Private Limited, IndiaGoogle Scholar
  8. 8.
    Specht DF (1990) Probabilistic neural networks. Neural Netw 3(109):118Google Scholar
  9. 9.
    Shah FA, Sukumar RA, Anto BP (2010) Discrete Wavelet transforms and artificial neural networks for speech emotion recognition. Int J Comput Theor Eng 2(3)Google Scholar
  10. 10.
    Sripathi D (2003) Chapter 2, The discrete wavelet transform. Available at
  11. 11.
    Long CL, Datta S (1996) Wavelet based feature extraction for phoneme recognition. In: Proceedings of 4h international conference on spoken language, vol 1Google Scholar
  12. 12.
    Rabiner LR, Schafer RW (2009) Digital processing of speech signals. Pearson Education, Dorling Kindersley (India) Pvt Ltd, IndiaGoogle Scholar
  13. 13.
    Tang BT, Lang R, Schroder H (1994) Applying wavelet analysis to speech segmentation and classification. Wavelet applications. In: Proceedings of SPIE, 2242Google Scholar

Copyright information

© Springer India 2014

Authors and Affiliations

  1. 1.Department of Electronics and Communication EngineeringGauhati UniversityGuwahatiIndia
  2. 2.Department of Electronics and Communication TechnologyGauhati UniversityGuwahatiIndia

Personalised recommendations