Learning Speech as Acoustic Sequences with the Unsupervised Model , TOM

  title={Learning Speech as Acoustic Sequences with the Unsupervised Model , TOM},
  author={St{\'e}phane Durand and Fr{\'e}d{\'e}ric Alexandre},
Most connectionist systems do not involve the temporal dimension. However, some neural networks attempt to take time into account either inside or outside the network. Speech recognition is a stochastic problem that involves a dynamic parameter. The recognitionof a unit of speech depends on the contextual information i.e., the parts around it. Our approach consists of interpreting the speech signal as a sequence of acoustic informationand designing a neural network, called TOM or Temporal… CONTINUE READING
2 Citations
7 References
Similar Papers


Publications citing this paper.
Showing 1-2 of 2 extracted citations


Publications referenced by this paper.
Showing 1-7 of 7 references

Plausible selforganizing maps for speech recognition

  • L. Beaugé, S. Durand, F. Alexandre
  • Artificial neural nets and genetic algorithms,
  • 1993
1 Excerpt

A ”neural-gas” network learns topologies

  • T. M. Martinetz, K. J. Schulten
  • Artificial Neural Network,
  • 1991
3 Excerpts

Phonotopic maps – insightful representation of phonological features for speech recognition

  • T. Kohonen, K. Makisara, T. Saramaki
  • In IEEE Proceedings of the 7th International…
  • 1984
2 Excerpts

Similar Papers

Loading similar papers…