Spectral Subtraction Using Spectral Harmonics for Robust Speech Recognition in Car Environments

  • Jounghoon Beh
  • Hanseok Ko
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2660)

Abstract

This paper addresses a novel noise-compensation scheme to solve the mismatch problem between training and testing condition for the automatic speech recognition (ASR) system, specifically in car environment. The conventional spectral subtraction schemes rely on the signal-to-noise ratio (SNR) such that attenuation is imposed on that part of the spectrum that appears to have low SNR, and accentuation is made on that part of high SNR. However, since these schemes are based on the postulation that the power spectrum of noise is in general at the lower level in magnitude than that of speech. Therefore, while such postulation is adequate for high SNR environment, it is grossly inadequate for low SNR scenarios such as that of car environment. This paper proposes an efficient spectral subtraction scheme focused specifically to low SNR noisy environment by representing harmonics distinctively in speech spectrum. Representative experiments confirm the superior performance of the proposed method over conventional methods. The experiments are conducted using car noise-corrupted utterances of Aurora2 corpus.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Jensen, J., Hansen, J.: Speech Enhancement Using a Con-strained Iterative Sinusoidal Model, IEEE Transactions on Speech and Audio Processing, Vol. 9, No. 7, Oct (2001) 731–740CrossRefGoogle Scholar
  2. 2.
    Ealey, D., Kellher, H., Pearce, D.: Harmonic tunneling: track-ing non-stationary noises during speech, Eurospeech 2001(2001) 437–440Google Scholar
  3. 3.
    Berouti, M., Schwartz, R., Makhoul, J.: Enhancement of speech corrupted by additive noise, Proceedings of the IEEE Conference on Acoustics, Speech, and Signal Processing, April (1979) 208–211Google Scholar
  4. 4.
    Virag, N.: Single Channel Speech Enhancement Based on Masking Properties of the Human Auditory System, IEEE Transactions on Speech and Audio Processing, Vol. 7, No. 2, Mar (1999) 126–137CrossRefGoogle Scholar
  5. 5.
    Lockwood, P., Boudy, J.: Experiments with a Nonlinear Spectral Subtractor(NSS), Hidden Markov Models and the pro-jection, for robust speech recognition in cars, Speech Communication, Vol. 11 (1992) 215–228CrossRefGoogle Scholar
  6. 6.
    Hess, W.: Pitch Determination of Speech Signals, Springer-Verlag Berlin Heidelberg New York Tokyo (1983)Google Scholar
  7. 7.
    Rabiner, L., Schafer, R.: Digital Processing of Speech Signals, Prentice-Hall (1978)Google Scholar
  8. 8.
    Boll, S.F.: Suppression of Acoustic Noise in Speech Using Spectral Subtraction, IEEE Transaction on Acoustics, Speech and Signal Processing, Vol.27, No.2, April (1979) 113–120CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Jounghoon Beh
    • 1
  • Hanseok Ko
    • 1
  1. 1.Departments of Electronics and Computer EngineeringKorea UniversitySeoulKorea

Personalised recommendations