REMAP-experiments with speech recognition

  title={REMAP-experiments with speech recognition},
  author={Yochai Konig and Herv{\'e} Bourlard and Nelson Morgan},
In this report we present experimental and theoretical results using a framework for training and modeling continuous speech recognition systems based on the theoretically optimal Maximum a Posteriori (MAP) criterion. This is in constrast to most state-of-the-art systems which are trained according to a Maximum Likelihood (ML) criterion. Although the algorithm is quite general, we applied it to a particular form of hybrid system combining Hidden Markov Models (HMMs) and Artificial Neural… CONTINUE READING
5 Citations
10 References
Similar Papers


Publications referenced by this paper.
Showing 1-10 of 10 references

Connectionist Speech Recognition - A Hybrid Approach

  • H. Bourlard, N. Morgan
  • Kluwer Academic Publishers,
  • 1994
Highly Influential
12 Excerpts

REMAP: Re- cursive estimation and maximization of a posteriori probabilities, application to transition-based connec- tionist speech recognition

  • H. Bourlard, Y. Konig, N. Morgan
  • Technical Report TR-94- 064,
  • 1994
Highly Influential
3 Excerpts

An input output HMM ar- chitecture

  • Y. Bengio, P. Frasconi
  • Advances in Neural Information Processing…
  • 1995

Similar Papers

Loading similar papers…