Confidence Score Based Unsupervised Incremental Adaptation for OOV Words Detection

  • Wei Chu
  • Xi Xiao
  • Jia Liu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4109)

Abstract

This paper presents a novel approach of distinguishing in-vocabulary (IV) words and out-of-vocabulary (OOV) words by using confidence score-based unsupervised incremental adaptation. The unsupervised adaptation uses Viterbi decode results which have high confidence scores to adjust new acoustic models. The adjusted acoustic models can award IV words and punish OOV words in confidence score, thus obtain the goal of separating IV and OOV words. Our Automatic Speech Recognition Laboratory has developed a Speech Recognition Developer Kit (SRDK) which serves as a baseline system for different speech recognition tasks. Experiments conducted on the SRDK system have proved that this method can achieve a rise over 41% in OOV words detection rate (from 68% to 96%) at the same cost of a false alarm (taken IV words as OOV words) rate of 10%. This method also obtains a rise over 11% in correct acceptance rate (from 88% to 98%) at the same cost of a false acceptance rate of 20%.

References

  1. 1.
    Cox, S., Rose, R.: Confidence measures for the SWITCHBOARD database. In: Proceedings of ICASSP 1996, Atlanta, pp. 511–514 (1996)Google Scholar
  2. 2.
    Hazen, T.J., Seneff, S., Polifroni, J.: Recognition confidence scoring and its use in speech understanding systems. Computer Speech and Language 16(1), 49–67 (2002)CrossRefGoogle Scholar
  3. 3.
    Sankar, A., Wu, S.-L.: Utterance verification based on statistics of phone-level confidence scores. In: Proceedings of ICASSP 2003, Menlo Park, pp. 584–587 (2003)Google Scholar
  4. 4.
    Boite, J., Bourlard, H., D’hoore, B., Haesen, M.: A new approach towards keyword spotting. In: Proceedings of Eurospeech 1993, Berlin, pp. 1273–1276 (1993)Google Scholar
  5. 5.
    Wang, D., Narayanan, S.S.: A confidence-score based unsupervised map adaptation for speech recognition. In: Proceedings of 36th Conference on Signal, Systems and Computers, Pacific Grove, pp. 222–226 (2002)Google Scholar
  6. 6.
    Charlet, D.: Confidence-measure-driven unsupervised incremental adaptation for HMM-based speech recognition. In: Proceedings of ICASSP 2001, Salt Lake City, pp. 357–360 (2001)Google Scholar
  7. 7.
    Leggetter, C.J., Woodland, P.C.: Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Computer Speech and Language 9(2), 171–185 (1995)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Wei Chu
    • 1
  • Xi Xiao
    • 1
  • Jia Liu
    • 1
  1. 1.Department of Electronic EngineeringTsinghua UniversityBeijingChina

Personalised recommendations