A Constrained Line Search Optimization Method for Discriminative Training of HMMs

@article{Liu2008ACL,
  title={A Constrained Line Search Optimization Method for Discriminative Training of HMMs},
  author={Peng Liu and Cong Liu and Hui Jiang and Frank K. Soong and Ren-Hua Wang},
  journal={IEEE Transactions on Audio, Speech, and Language Processing},
  year={2008},
  volume={16},
  pages={900-909}
}
In this paper, we propose a novel optimization algorithm called constrained line search (CLS) for discriminative training (DT) of Gaussian mixture continuous density hidden Markov model (CDHMM) in speech recognition. The CLS method is formulated under a general framework for optimizing any discriminative objective functions including maximum mutual information (MMI), minimum classification error (MCE), minimum phone error (MPE)/minimum word error (MWE), etc. In this method, discriminative… CONTINUE READING
Highly Cited
This paper has 26 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 15 extracted citations

Analysis of Extended Baum–Welch and Constrained Optimization for Discriminative Training of HMMs

IEEE Transactions on Audio, Speech, and Language Processing • 2012
View 9 Excerpts
Highly Influenced

HMM parameters estimation with inequality constraints

Proceedings of the 32nd Chinese Control Conference • 2013
View 1 Excerpt

Overview of large scale optimization for discriminative training in speech recognition

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2012
View 1 Excerpt

Large-Margin Estimation of Hidden Markov Models With Second-Order Cone Programming for Speech Recognition

IEEE Transactions on Audio, Speech, and Language Processing • 2011
View 1 Excerpt

References

Publications referenced by this paper.
Showing 1-10 of 21 references

Minimum Phone Error and I-smoothing for improved discriminative training

2002 IEEE International Conference on Acoustics, Speech, and Signal Processing • 2002
View 9 Excerpts
Highly Influenced

Minimum classification error rate methods for speech recognition

IEEE Trans. Speech and Audio Processing • 1997
View 8 Excerpts
Highly Influenced

Maximum mutual information estimation, and the speech recognition problem

Y. Normandin, H. M. Models
Ph.D. dissertation, Dept. Elect. Eng., McGill Univ., Montreal, QC, Canada, 1991. (29) Authorized licensed use limited to: York University. Downloaded on June 02,2010 at 08:41:44 UTC from IEEE Xplore. Restrictions apply. LIU et al.: CONSTRAINED LINE SEARCH OPTIMIZATION METHOD FOR DISCRIMINATIVE TRAI • 1991
View 10 Excerpts
Highly Influenced

Discriminative training based on the criterion of least phone competing tokens for large vocabulary speech recognition

Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005. • 2005
View 1 Excerpt

Statistical performance analysis of MCE/GPD learning in Gaussian classifiers and hidden Markov models [speech recognition example]

Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005. • 2005
View 1 Excerpt

Similar Papers

Loading similar papers…