Phonetic Feature Discovery in Speech Using Snap-Drift Learning

  • Sin Wee Lee
  • Dominic Palmer-Brown
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4132)


This paper presents a new application of the snap-drift algorithm [1]: feature discovery and clustering of speech waveforms from non-stammering and stammering speakers. The learning algorithm is an unsupervised version of snap-drift which employs the complementary concepts of fast, minimalist learning (snap) & slow drift (towards the input pattern) learning. The Snap-Drift Neural Network (SDNN) is toggled between snap and drift modes on successive epochs. The speech waveforms are drawn from a phonetically annotated corpus, which facilitates phonetic interpretation of the classes of patterns discovered by the SDNN.


Input Pattern Category Type Speech Utterance Input Waveform Speaker Group 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lee, S.W., Palmer-Brown, D., Roadknight, C.M.: Performance-guided Neural Network for Rapidly Self-Organising Active Network Management. Neurocomputing 61C, 5–20 (2004)CrossRefGoogle Scholar
  2. 2.
    Aylett, M., Turk, A.: Vowel Quality in Spontaneous Speech: What makes a good vowel. In: Proc. of Int. Conf. of Spoken Language Processing, Sydney, AustraliaGoogle Scholar
  3. 3.
    Klatt, D.H.: Review of Text-to-Speech Conversion for English. Online collection (1987)Google Scholar
  4. 4.
    Ladefoged, P.: A Course in Phonetics, 4th edn., Boston, Heinle & Heinle (2001)Google Scholar
  5. 5.
    Lee, S.W., Palmer-Brown, D., Tepper, J., Roadknight, C.M.: Snap-Drift: Real-time Performance-guided Learning. In: Proc. of IJCNN, vol. 2, Portland, Oregon, pp. 1412–1416 (2003)Google Scholar
  6. 6.
    Lee, S.W., Palmer-Brown, D., Roadknight, C.M.: Reinforced Snap-Drift Learning for Proxylet Selection in Active Computer Networks. In: Proc. of IJCNN, Budapest, Hungary, vol. 2, pp. 1545–1550 (2004)Google Scholar
  7. 7.
    Donelan, H., Pattinson, C., Palmer-Brown, D., Lee, S.W.: The Analysis of Network Manager’s Behaviour using a Self-Organising Neural Networks. In: Proc. of ESM, Magdeburg, Germany, pp. 111–116 (2004)Google Scholar
  8. 8.
    Lee, S.W., Palmer-Brown, D.: Phrase Recognition using Snap-Drift Learning Algorithm. In: Proc. of IJCNN, Montreal, Canada (2005)Google Scholar
  9. 9.
    Garside, R., Leech, G., Varadi, T.: Manual of Information to Accompany the Lancaster Parsed Corpus: Department of English, University of Oslo (1987)Google Scholar
  10. 10.
    Carpenter, G.A., Grossberg, S.: A Massively Parallel Architecture for a Self-Organising Neural Pattern Recognition Machine. Com. Vision, Graphics and Image Proc. 37, 54–115 (1987)CrossRefGoogle Scholar
  11. 11.
    Kohonen, T.: Improved Versions of Learning Vector Quantization. In: Proc. of IJCNN, vol. 1, pp. 545–550 (1990)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Sin Wee Lee
    • 1
  • Dominic Palmer-Brown
    • 1
  1. 1.Innovative Informatics Research GroupUniversity of East LondonEssexUK

Personalised recommendations