ML parameter estimation of a multiscale stochastic process using the EM algorithm

@article{Kannan2000MLPE,
  title={ML parameter estimation of a multiscale stochastic process using the EM algorithm},
  author={Ashvin Kannan and Mari Ostendorf and W. Clem Karl and David A. Casta{\~n}{\'o}n and Randall K. Fish},
  journal={IEEE Trans. Signal Processing},
  year={2000},
  volume={48},
  pages={1836-1840}
}
An algorithm for estimation of the parameters of a multiscale stochastic process based on scale-recursive dynamics on trees is presented. The expectation-maximization algorithm is used to provide maximum likelihood estimates for the general case of a nonhomogeneous tree with no fixed structure for the process dynamics. Experimental results are presented using synthetic data. 

References

Publications referenced by this paper.
Showing 1-10 of 13 references

Adaptation of spectral trajectory models for large vocabulary continuous speech recognition

  • A. Kannan
  • Ph.D. dissertation, Boston Univ., Boston, MA…
  • 1997
1 Excerpt

Maximum-likelihood estimation of multiscale stochastic model parameters

  • K. C. Chou
  • presented at the Proc. of the IEEE-SP Int. Symp…
  • 1996
1 Excerpt

A multiscale stochastic modeling approach to the monitoring of mechanical systems

  • K. C. Chou, L. P. Heck
  • Proc. IEEE-SP Int. Symp. Time-Freq. Time-Scale…
  • 1994
1 Excerpt

Similar Papers

Loading similar papers…