A constrained joint optimization method for large margin HMM estimation

@article{Li2005ACJ,
  title={A constrained joint optimization method for large margin HMM estimation},
  author={Xinwei Li and Hui Jiang},
  journal={IEEE Workshop on Automatic Speech Recognition and Understanding, 2005.},
  year={2005},
  pages={151-156}
}
  • Xinwei Li, Hui Jiang
  • Published 2005 in
    IEEE Workshop on Automatic Speech Recognition and…
In this paper, we propose a new optimization method, i.e., constrained joint optimization method, to solve the minimax optimization problem in large margin estimation (LME) of continuous density hidden Markov model (CDHMM) for speech recognition. First, we mathematically analyze the definition of margin and introduce some theoretically-sound constraints into the minimax optimization to guarantee the boundedness of the margin in LME. Moreover, we propose to solve this constrained minimax… CONTINUE READING
Highly Cited
This paper has 18 citations. REVIEW CITATIONS
13 Citations
18 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 13 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 18 references

Discriminative Training for Large Margin HMMs

  • H. Jiang
  • Technical Report CS-2004-01,
  • 2004

Hfomann, ”Large margin methods for label sequence learning,

  • T. Y. Altun
  • Proc. of Eurospeech 2003,
  • 2003

Pattern recognition using a generalized probabilistic descent method,

  • S. Katagiri, B.-H. Juang, C.-H. Lee
  • Proceedings of the IEEE,
  • 1998
1 Excerpt

Minimum Classifi cation Error Rate Methods for Speech Recognition

  • B.-H. Juang, W. Chou, C.-H. Lee
  • IEEE Trans. on Speech and Audio Processing, pp…
  • 1997
1 Excerpt

Similar Papers

Loading similar papers…