Advanced search
Publication Cover
Network: Computation in Neural Systems Volume 8, 1997 - Issue 4
Submit an article Journal homepage
8
Views
5
CrossRef citations to date
0
Altmetric
Original Article

Generalisation and discrimination emerge from a self-organising componential network: a speech example

Chris J S Webber Defence Evaluation and Research Agency, St Andrews Road, Malvern, Worcestershire, WR14 3PS, UK
Pages 425-440 | Received 24 Jul 1996, Published online: 09 Jul 2009

References

  • Barlow H B. Unsupervised learning. Neural Comput. 1989; 1: 295–311
  • Bridle J S. Alpha-nets: a recurrent ‘neural’ network architecture with a hidden Markov model interpretation. Speech Commun. 1990; 9: 83–92
  • Carpenter G A, Grossberg S. The adaptive resonance theory of adaptive pattern recognition by a self-organising neural network. Computer March, 1988; 77–88
  • Dayan P, Hinton G. Varieties of Helmholtz machine. Neural Networks 1996; 9: 1385–403
  • Field D J. What is the goal of sensory coding?. Neural Comput. 1994; 6: 559–601
  • Foldiak P. Forming sparse representations by local anti-Hebbian learning. Biol. Cybern. 1990; 64: 165–70
  • Friedman J H, Tukey J W. A projection pursuit algorithm for exploratory data analysis. IEEE Trans. Comput. 1974; C-23: 881–90
  • Fukushima K, Miyake S. Neocognitron: a new algorithm for pattern recognition tolerant of deformations and shifts in position. Pattern Recogn. 1982; 15: 455–69
  • Hebb D O. The Organisation of Behavior. Wiley, New York 1949
  • Hinton G, Zemel R. Autoencoders, minimum description-length and Helmholtz free energy. Advances in Neural Information Processing Systems, J Cowan, et al. Morgan Kaufmann, San Mateo, CA 1994; 6: 3–10
  • Huber P J. Projection pursuit. Ann. Stat. 1985; 13: 435–75
  • Intrator N. Feature extraction using an unsupervised neural network. Neural Comput. 1992; 4: 98–107
  • Iwamida H, Katagiri S, McDermott E, Tohkura Y (1990) A hybrid speech recognition system using HMMs with an LVQ-trained codebook. 1990 Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Albuquerque, NM, April, 1990. IEEE, Piscataway, NJ, 489–92
  • Kohonen T (1982) Clustering taxonomy and topological maps of patterns. Proc. 6th IEEE Int. Conf. on Pattern Recognition, Munich, October, 1982. IEEE, Piscataway, NJ, 114–28
  • Kohonen T, Torkkola K, Shozakai M, Kangas J, Ventä O (1988) Phonetic typewriter for Finnish and Japanese. Proc., 1988, IEEE Int. Conf. on Acoustics, Speech and Signal Processing, New York, April, 1988. IEEE, Piscataway, NJ, 607–10
  • Luttrell S P. Self-supervised adaptive networks. IEE Proc. F 1992; 139: 371–7
  • McDermott E, Katagiri S (1989) Shift-invariant, multi-category phoneme recognition using Kohonen's LVQ2. Proc., 1989, IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Glasgow, May, 1989. IEEE, Piscataway, NJ, 81–4
  • Nowell P, Moore R K (1995) The application of dynamic programming techniques to non-word based topic spotting. Proc. 4th Eur. Conf. on Speech Communications and Technology, Madrid, September, 1995, J M Pardo, et al. 1355–8, (ESCA)
  • Oja E. A simplified neuron model as a principal component analyser. J. Math. Biol. 1982; 15: 267–73
  • Olshausen B A, Field D J. Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 1996; 381: 607–9
  • Robinson A J. An application of recurrent nets to phone probability estimation. IEEE Trans. Neural Networks 1994; 5: 229–39
  • Rumelhart D E, Hinton G E, Williams R J. Learning internal representations by error propagation. Parallel Distributed Processing. MIT Press, Cambridge, MA 1986; 1
  • Russell M J, Moore R K, Tomlinson M J, Deacon J C A. RSRE speech database recordings. Part II: Recordings made for automatic speech recognition assessment and research. MalvernUK 1983, RSRE report 84008, DRA
  • Sankoff D, Kruskal J B. An anthology of algorithms and concepts for sequence comparison. Time Warps, String Edits, and Macromolecules: the Theory and Practice of Sequence Comparison. Addison-Wesley, Reading, MA 1983
  • Saund E. A multiple cause mixture model for unsupervised learning. Neural Comput. 1994; 7: 57–71
  • Skilling A I, Nowell P, Moore R K. Acoustic based topic-spotting. 1994, unpublished report
  • Tattersall G D, Johnston R D. Self-organising arrays for speech recognition. Proc. Inst. Acoust. 1984; 6: 323–31
  • Webber C J S. Self-organisation of transformation-invariant detectors for constituents of perceptual patterns. Network: Comput. Neural Syst. 1994; 5: 471–96
  • Yu G, Russel W, Schwartz R, Makhoul J (1990) Discriminant analysis and supervised vector quantisation for continuous speech recognition. Proc., 1990, IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Albuquerque, NM, April, 1990. IEEE, Piscataway, NJ, 685–8
  • Zemel R. A minimum description-length framework for unsupervised learning. University of Toronto. 1993, PhD Thesis
  • Ziv J, Lempel A. A universal algorithm for sequential data compression. IEEE Trans. Inf. Theory 1977; IT-23: 337–43

Reprints and Corporate Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

To request a reprint or corporate permissions for this article, please click on the relevant link below:

Order Reprints Request Corporate Permissions

Academic Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

Obtain permissions instantly via Rightslink by clicking on the button below:

Request Academic Permissions

If you are unable to obtain permissions via Rightslink, please complete and submit this Permissions form. For more information, please visit our Permissions help page.

Related research

People also read lists articles that other readers of this article have read.

Recommended articles lists articles that we recommend and is powered by our AI driven recommendation engine.

Cited by lists all citing articles based on Crossref citations.
Articles with the Crossref icon will open in a new tab.