Abstract
In this paper, we propose a novel approach that reduces the confidence error rate of traditional posterior probability-based confidence measures in large vocabulary continuous speech recognition systems. The method enhances the discriminability of confidence measures by applying entropy information to the posterior probability-based confidence measures of word hypotheses. The experiments conducted on the Chinese Mandarin broadcast news database MATBN show that entropy-based confidence measures outperform traditional posterior probability-based confidence measures. The relative reductions in the confidence error rate are 14.11% and 9.17% for experiments conducted on field reporter speech and interviewee speech, respectively.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Chen, B., Kuo, J.-W., Tsai, W.-H.: Lightly Supervised and Data-driven Approaches to Mandarin Broadcast News Transcription. International Journal of Computational Linguistics and Chinese Language Processing 10(1), 1–18 (2005)
Wessel, F., Schlüter, R., Ney, H.: Using Posterior Probabilities for Improved Speech Recognition. In: Proc. ICASSP 2000 (2000)
Lo, W.K., Soong, F.K.: Generalized Posterior Probability for Minimum Error Verification of Recognized Sentences. In: Proc. ICASSP 2005 (2005)
Rose, R.C., Juang, B.-H., Lee, C.-H.: A Training Procedure for Verifying String Hypothesis in Continuous Speech Recognition. In: Proc. ICASSP 1995 (1995)
Wessel, F., Schlüter, R., Ney, H.: Confidence Measures for Large Vocabulary Continuous Speech Recognition. IEEE Trans. Speech and Audio Processing 9(3), 288–298 (2001)
Lo, W.K., Soong, F.K., Nakamura, S.: Generalized Posterior Probability for Minimizing Verification Errors at Subword, Word and Sentence Levels. In: Proc. ISCSLP (2004)
Xue, J., Zhao, Y.: Random Forests-based Confidence Annotation Using Novel Features from Confusion Network. In: Proc. ICASSP 2006 (2006)
Gales, H.J.F.: Semi-tied Covariance Matrices for Hidden Markov Models. IEEE Trans. on Speech and Audio Processing 7(3), 272–281 (1999)
Wang, H.-M., Chen, B., Kuo, J.-W., Cheng, S.-S.: MATBN: A Mandarin Chinese Broadcast News Corpus. International Journal of Computational Linguistics and Chinese Language Processing 10(2), 219–236 (2005)
Povey, D.: Discriminative Training for Large Vocabulary Speech Recognition. Ph. D Dissertation, Peterhouse, University of Cambridge (2004)
Tseng, S.C., Liu, Y.F.: Mandarin Conversational Dialogue Corpus. MCDC. Technical Note 2001-01, Institute of Linguistics, Academia Sinica, Taipei
Stolcke, A.: SRI language Modeling Toolkit version 1.3.3, http://www.speech.sri.com/projects/srilm/
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chen, TH., Chen, B., Wang, HM. (2006). On Using Entropy Information to Improve Posterior Probability-Based Confidence Measures. 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_48
Download citation
DOI: https://doi.org/10.1007/11939993_48
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)