A two-channel training algorithm for hidden Markov model to identify visual speech elements

@article{Foo2003ATT,
  title={A two-channel training algorithm for hidden Markov model to identify visual speech elements},
  author={Say Wei Foo and Yong Lian and Liang Dong},
  journal={Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03.},
  year={2003},
  volume={2},
  pages={II-II}
}
A novel two-channel algorithm is proposed in this paper for discriminative training of Hidden Markov Models (HMMs). It adjusts the symbol emission coefficients of an existing HMM to maximize the separable distance between a pair of confusable training samples. The method is applied to identify the visemes of visual speech. The results indicate that the two-channel training method provides better accuracy on separating similar visemes than the conventional Baum-Welch estimation. 

Similar Papers

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-3 OF 3 REFERENCES

Maximum mutual information estimation of hidden Markov model parameters for speech recognition

  • ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing
  • 1986

On the convergence properties of the EM algorithm.”Annua/s ofStatistics, Vol. 1 I

C.F.J. Wu
  • 1983