Skip to main content
SpringerLink
Log in

Investigation of improved approaches to bayes risk decoding

  • Published:
Journal of Shanghai Jiaotong University (Science) Aims and scope Submit manuscript

Abstract

Bayes risk (BR) decoding methods have been widely investigated in the speech recognition area due to its flexibility and complexity compared with the maximum a posteriori (MAP) method regarding to minimum word error (MWE) optimization. This paper investigates two improved approaches to the BR decoding, aiming at minimizing word error. The novelty of the proposed methods is shown in the explicit optimization of the objective function, the value of which is calculated by an improved forward algorithm on the lattice. However, the result of the first method is obtained by an expectation maximization (EM) like iteration, while the result of the second one is achieved by traversing the confusion network (CN), both of which lead to an optimized objective function value with distinct approaches. Experimental results indicate that the proposed methods result in an error reduction for lattice rescoring, compared with the traditional CN method for lattice rescoring.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Levenshtein V I. Binary codes capable of correcting deletions, insertions and reversals [J]. Soviet Physics Doklady, 1966, 10(8): 707–710.

    MathSciNet  Google Scholar 

  2. Stolcke A, Konig Y, Weintraub M. Explicit word error minimization in n-best list rescoring [C]//Proceedings of the 5th European Conference on Speech Communication and Technology. Rhodes, Greece: ISCA, 1997: 163–166.

    Google Scholar 

  3. Mangu L, Brill E, Stolcke A. Finding consensus in speech recognition: Word error minimization and other applications of confusion networks [J]. Computer Speech and Language, 2000, 14: 373–400.

    Article  Google Scholar 

  4. Goel V, Kumar S, Byrne W J. Minimum bayes-risk automatic speech recognition [J]. Computer Speech and Language, 2000, 14: 115–135.

    Article  Google Scholar 

  5. Wessel F, Schluter R, Ney H. Explicit word error minimization using word hypothesis posterior probabilities [C]//Proceeding of International Conference on Acoustics, Speech, and Signal Processing. Salt Lake City, USA: IEEE, 2001: 33–36.

    Google Scholar 

  6. Goel V, Byrne W J. Segmental minimum bayes-risk decoding for automatic speech recognition [J]. IEEE Transactions on Speech and Audio Processing, 2006, 12: 234–249.

    Article  Google Scholar 

  7. Xu H, Povey D, Zhu J, et al. Minimum hypothesis phone error as a decoding method for speech recognition [C]//Proceedings of INTERSPEECH. Brighton, UK: ISCA, 2009: 76–79.

    Google Scholar 

  8. Povey D, Woodland P C. Minimum phone error and I-smoothing for improved discriminative training [C]//Proceeding of International Conference on Acoustics, Speech, and Signal Processing. Florida, USA: IEEE, 2002: 105–108.

    Google Scholar 

  9. Hoffmeister B, Schluter R, Ney H. Bayes risk approximations using time overlap with an application to system combination [C]// Proceedings of INTERSPEECH. Brighton, UK: ISCA, 2009: 1191–1194.

    Google Scholar 

  10. Heigold G, Macherey W, Schluter R, et al. Minimum exact word error training [C]// Proceedings of Automatic Speech Recognition and Understanding. San Juan, USA: IEEE, 2005: 186–190.

    Chapter  Google Scholar 

  11. Xu H, Povey D, Mangu L, et al. An improved consensus-like method for minimum Bayes risk decoding and lattice combination [C]//Proceedings of International Conference on Acoustics, Speech, and Signal Processing. Dallas, USA: IEEE, 2010: 4938–4941.

    Google Scholar 

  12. Stolcke A. SRILM — An extensible language modeling toolkit [C]//Proceedings of International Conference on Spoken Language Processing. Denver, USA: ISCA, 2002: 901–904.

    Google Scholar 

  13. Fiscus J G. A post-processing system to yield reduced word error rates: Recognizer output error reduction (ROVER) [C]// Proceedings of Automatic Speech Recognition and Understanding. Santa Barbara, USA: IEEE, 1997: 347–354.

    Chapter  Google Scholar 

  14. Young S, Evermanna G, Gales M, et al. The HTK book [M]. 3rd ed. Cambridge: Cambridge University, 2006.

    Google Scholar 

  15. Povey D, Kanevsky D, Kingsbury B, et al. Boosted MMI for model and feature-space discriminative training recognition [C]// Proceedings of International Conference on Acoustics, Speech, and Signal Processing. Las Vegas, USA: IEEE, 2008: 4057–4060.

    Google Scholar 

  16. Ortmanns S, Ney H. A word graph algorithm for large vocabulary continuous speech recognition [J]. Computer Speech and Language, 1997, 11: 43–72.

    Article  Google Scholar 

  17. Povey D. Discriminative training for large vocabulary speech recognition [M]. Cambridge: Cambridge University, 2004.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electronic Engineering, Shanghai Jiaotong University, Shanghai, 200240, China

    Hai-hua Xu  (徐海华) & Jie Zhu  (朱 杰)

Authors
  1. Hai-hua Xu  (徐海华)
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jie Zhu  (朱 杰)
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hai-hua Xu  (徐海华).

Rights and permissions

Reprints and permissions

About this article

Cite this article

Xu, Hh., Zhu, J. Investigation of improved approaches to bayes risk decoding. J. Shanghai Jiaotong Univ. (Sci.) 16, 524–529 (2011). https://doi.org/10.1007/s12204-011-1189-1

Download citation

  • Received:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12204-011-1189-1

Key words

CLC number

Search

Navigation