Advertisement

Performance Improvement in Multiple-Model Speech Recognizer under Noisy Environments

  • Jang-Hyuk Yoon
  • Yong-Joo Chung
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6218)

Abstract

Multiple-model speech recognizer has been shown to be quite successful in noisy speech recognition. However, its performance has usually been tested using the general speech front-ends which do not incorporate any noise adaptive algorithms. For the accurate evaluation of the effectiveness of the multiple-model frame in noisy speech recognition, we used the state-of-the-art front-ends and compared its performance with the well-known multi-style training method. In addition, we improved the multiple-model speech recognizer by employing N-best reference HMMs for interpolation and using multiple SNR levels for training each of the reference HMM.

Keywords

speech recognition multiple-model frame noise robustness MTR DSR Aurora database 

References

  1. 1.
    Gales, M.J.F.: Model Based Techniques for Noise-Robust Speech Recognition, Ph.D. Dissertation, University of Cambridge (1995)Google Scholar
  2. 2.
    Moreno, P.J.: Speech Recognition in Noisy Environments, Ph.D. Dissertation, Carnegie Mellon University (1996)Google Scholar
  3. 3.
    Ball, S.F.: Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans. Acoust., Speech, Signal Process. 27, 113–120 (1979)CrossRefGoogle Scholar
  4. 4.
    Xu, H., Tan, Z.-H., Dalsgaard, P., Lindberg, B.: Robust Speech Recognition on Noise and SNR Classification – a Multiple-Model Framework. In: Proc. Interspeech (2005)Google Scholar
  5. 5.
    ETSI draft standard doc. Speech Processing, Transmission and Quality aspects (STQ); Distributed speech recognition; Front-end feature extraction algorithm; Compression algorithm, ETSI Standard ES 202 108 (2000)Google Scholar
  6. 6.
    ETSI draft standard doc. Speech Processing, Transmission and Quality aspects (STQ); Distributed speech recognition; Advanced Front-end feature extraction algorithm; Compression algorithm, ETSI Standard ES 202 050 (2002)Google Scholar
  7. 7.
    Macho, D., Mauuary, L., Noe, B., Cheng, Y., Eahey, D., Jouvet, D., Kelleher, H., Pearce, D., Saadoun, F.: Evaluation of a noise-robust DSR front-end on Aurora databases. In: Proc. ICSLP, pp. 17–20 (2002)Google Scholar
  8. 8.
    Juang, B.H., Rabiner, L.R.: A Probabilistic Distance Measure for Hidden Markov Models. AT&T Technology Journal, 391–408 (1984)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Jang-Hyuk Yoon
    • 1
  • Yong-Joo Chung
    • 1
  1. 1.Department of ElectronicsKeimyung UniversityDaeguS. Korea

Personalised recommendations