Skip to main content

Improved Large Vocabulary Continuous Chinese Speech Recognition by Character-Based Consensus Networks

  • Conference paper
Chinese Spoken Language Processing (ISCSLP 2006)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 4274))

Included in the following conference series:

Abstract

Word-based consensus networks have been verified to be very useful in minimizing word error rates (WER) for large vocabulary continuous speech recognition for western languages. By considering the special structure of Chinese language, this paper points out that character-based rather then word-based consensus networks should work better for Chinese language. This was verified by extensive experimental results also reported in the paper.

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

Access this chapter

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Bahl, L.R., Jelinek, F., Mercer, R.L.: A Maximum Likelihood Approach to Continuous Speech Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 5(2), 170–190 (1983)

    Article  Google Scholar 

  2. Stolcke, A., Konig, Y., Weintraub, M.: Explicit Word Error Minimization in N-best List Rescoring. In: Proc. Eurospeech, pp. 163–166 (1997)

    Google Scholar 

  3. Mangu, L., Brill, E., Stolckes, A.: Finding Consensus in Speech Recognition: Word Error Minimizaiton and Other Applications of Confusion Networks. Computer Speech and Language 14(4), 373–400 (2000)

    Article  Google Scholar 

  4. Soong, F.K., Lo, W.K., Nakamura, S.: Generalized Word Posterior Probability (GWPP) for Measuring Reliability of Reconized Words. In: Proc. SWIM 2004 (2004)

    Google Scholar 

  5. Soong, F.K., Lo, W.K., Nakamura, S.: Optimal Acoustic and Language Model Weights for Minimizing Word Verification Errors. In: Proc. ICSLP 2004 (2004)

    Google Scholar 

  6. Qian, Y., Soong, F.K., Lee, T.: Tone-enhanced Generalized Character Posterior Probability (GCPP) for Cantonese LVCSR. In: Proc. ICASSP 2006 (2006)

    Google Scholar 

  7. Wessel, F., Schluter, R., Ney, H.: Using Posterior Probabilities for Improved Speech Recognition. In: Proc., ICASSP (2000)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2006 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Fu, YS., Pan, YC., Lee, Ls. (2006). Improved Large Vocabulary Continuous Chinese Speech Recognition by Character-Based Consensus Networks. In: Huo, Q., Ma, B., Chng, ES., Li, H. (eds) Chinese Spoken Language Processing. ISCSLP 2006. Lecture Notes in Computer Science(), vol 4274. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11939993_45

Download citation

  • DOI: https://doi.org/10.1007/11939993_45

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-49665-6

  • Online ISBN: 978-3-540-49666-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics