Modeling human word recognition with sequences of artificial neurons

  • P. Wittenburg
  • D. van Kuijk
  • T. Dijkstra
Oral Presentations: Cognitive Science and AI Cognitive Science and AI II: Symbolic Processing
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1112)


A new psycholinguistically motivated and neural network based model of human word recognition is presented. In contrast to earlier models it uses real speech as input. At the word layer acoustical and temporal information is stored by sequences of connected sensory neurons which pass on sensor potentials to a word neuron. In experiments with a small lexicon which includes groups of very similar word forms, the model meets high standards with respect to word recognition and simulates a number of wellknown psycholinguistical effects.


Sensor Neuron Word Recognition Speech Signal Automatic Speech Recognition Automatic Speech Recognition System 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    McQueen, J.M. & Cutler,A. (in press). Cognitive Processes in Speech Perception. In W.J. Hardcastle & J. Laver (Eds.), A Handbook of Phonetic Science. Oxford: BlackwellGoogle Scholar
  2. [2]
    Norris, D.G. (1994). Shortlist: A connectionist model of continuous speech recognition. Cognition, 52(3), 1212–1232.Google Scholar
  3. [3]
    McClelland, J. & Elman,J.L. (1986). The TRACE model of speech perception. Cognitive Psychology, 18, 1–86Google Scholar
  4. [4]
    Morgan, N. & Bourlard, H. (1995). Connectionist Speech Recognition. Dordrecht:Kluwer.Google Scholar
  5. [5]
    Bourlard, H. (1995). Towards Increasing Speech Recognition Error Rates. Proceedings Eurospeech95, MadridGoogle Scholar
  6. [6]
    Wittenburg, P., van Kuijk, D. & Behnke, K. (1995) Automatic and Human Speech Recognition Systems: a Comparison. Proceedings 3. SNN Symposium, Nijmegen, NL.Google Scholar
  7. [7]
    Hermansky, H. & Morgan, N. (1994). RASTA processing of speech. IEEE Trans. Speech Audio, 2(4)Google Scholar
  8. [8]
    Hermansky, H. (1990). Perceptional Linear Predictive Analysis of Speech. J. Acoust. Soc. Am. 87 (4). 1738–1752Google Scholar
  9. [9]
    Waibel, A. et al. (1987). Phoneme Recognition Using Time-Delay Neural Networks. Technical Report TR-1-0006, ART Interpreting Telephony Research Laboratories.Google Scholar
  10. [10]
    Wittenburg, P. & Couwenberg, R. (1991). Recurrent Neural Networks as Phoneme Spotters. In T. Kohonen et al. (Eds.), Artificial Neural Networks. Amsterdam: North Holland.Google Scholar
  11. [11]
    Kohonen, T. (1989). Self-Organization and Associative Memory. Berlin: Springer Verlag.Google Scholar
  12. [12]
    van Kuijk, D.,Wittenburg, P. & Dijkstra, T. (1996). A connectionist model for the simulation of human spoken-word recognition. Proceedings of the 6th Workshop Computers in Psychology 1996, Amsterdam.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • P. Wittenburg
    • 1
  • D. van Kuijk
    • 1
  • T. Dijkstra
    • 2
  1. 1.Max-Planck-Institute for PsycholinguisticsNijmegen
  2. 2.NICIUniversity of NijmegenNijmegenThe Netherlands

Personalised recommendations