Discriminative Training for Large-Vocabulary Speech Recognition Using Minimum Classification Error

  title={Discriminative Training for Large-Vocabulary Speech Recognition Using Minimum Classification Error},
  author={Erik McDermott and Timothy J. Hazen and Jonathan Le Roux and Atsushi Nakamura and Shigeru Katagiri},
  journal={IEEE Transactions on Audio, Speech, and Language Processing},
The minimum classification error (MCE) framework for discriminative training is a simple and general formalism for directly optimizing recognition accuracy in pattern recognition problems. The framework applies directly to the optimization of hidden Markov models (HMMs) used for speech recognition problems. However, few if any studies have reported results for the application of MCE training to large-vocabulary, continuous-speech recognition tasks. This article reports significant gains in… CONTINUE READING
Highly Influential
This paper has highly influenced 124 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 724 citations. REVIEW CITATIONS
436 Extracted Citations
78 Extracted References
Similar Papers

Citing Papers

Publications influenced by this paper.
Showing 1-10 of 436 extracted citations

725 Citations

Citations per Year
Semantic Scholar estimates that this publication has 725 citations based on the available data.

See our FAQ for additional information.

Referenced Papers

Publications referenced by this paper.
Showing 1-10 of 78 references

Segmental GPD training of HMM based speech recognizer

  • W. Chou, B.-H. Juang, C.-H. Lee
  • Proc. IEEE ICASSP, Mar. 1992, vol. 1, pp. 473–476…
  • 1992
Highly Influential
4 Excerpts

Guest editorial

  • L. Deng, K. Wang, W. Chou
  • IEEE Signal Process. Mag., vol. 22, no. 5, pp. 12…
  • 2005

Similar Papers

Loading similar papers…