Layered markov models: a new architectural approach to automatic speech recognition

@article{Peagarikano2004LayeredMM,
  title={Layered markov models: a new architectural approach to automatic speech recognition},
  author={Mikel Pe{\~n}agarikano and Germ{\'a}n Bordel},
  journal={Proceedings of the 2004 14th IEEE Signal Processing Society Workshop Machine Learning for Signal Processing, 2004.},
  year={2004},
  pages={305-314}
}
This paper presents the theoretical basis of layered Markov models (LMM), which integrate all the knowledge levels commonly used in automatic speech recognition (acoustic, lexical and language levels) in a single model. Each knowledge level is represented by a set of Markov models (or even hidden Markov models) and all these sets are arranged in a layered structure. Given that common supervised training and recognition paradigms can be also expressed as simple Markov models, they can be… CONTINUE READING
2 Citations
6 References
Similar Papers

Citations

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

References

Publications referenced by this paper.
Showing 1-6 of 6 references

hang, "An introduction to hidden markov models," EEE Magazine on Accoustics

  • B.H.L.R. Rabiner
  • Speech and Signal Processing,
  • 1986

The dragon system - An overview,

  • J. K. Baker
  • IEEE Trans. Acoust. Speech Signal Processing, vol…
  • 1975

Statistical inference fur probabilistic functions of finite state Markov chains,

  • L. E. Baum, T. Petrie
  • Ann. Math. Stat.,
  • 1966

Similar Papers

Loading similar papers…