Adaptive noise spectral estimation for spectral subtraction speech enhancement

Adaptive noise spectral estimation for spectral subtraction speech enhancement

For access to this article, please select a purchase option:

Buy article PDF
(plus tax if applicable)
Buy Knowledge Pack
10 articles for £75.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Your details
Why are you recommending this title?
Select reason:
IET Signal Processing — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

An adaptive scheme for noise spectral estimation is proposed to cope with the power spectral subtraction method for speech enhancement. The use of such a noise spectral estimate helps eliminate residual noise without increasing speech distortion. Improvements in the segmental signal-to-noise ratio and modified bark spectral distortion measures are evidently seen with 192 TIMIT sentences corrupted by four types of broadband noise taken from the Noisex-92 database. Moreover, incorporation of this noise adaptation scheme into the constrained parameter estimator is demonstrated. Mean opinion score listening tests confirm that the proposed subtractive scheme yields better results than that acquired by subtracting an averaged noise power spectrum.


    1. 1)
      • Suppression of acoustic noise in speech using spectral subtraction
    2. 2)
      • Supplementary schemes to spectral subtraction for speech enhancement
    3. 3)
      • Berouti, M., Schwartz, R., Makhoul, J.: `Enhancement of speech corrupted by acoustic noise', Proc. IEEE Int. Conf. ASSP, 1979, p. 208–211
    4. 4)
      • Kamath, S.D., Loizou, P.C.: `A multi-band spectral subtraction method for enhancing speech corrupted by colored noise', Proc. IEEE Int. Conf. ASSP, 2002, p. 13–17
    5. 5)
      • All-pole modeling of degraded speech
    6. 6)
      • Paliwal, K.K., Basu, A.: `A speech enhancement method based on Kalman filtering', Proc. Int. Conf. ASSP, 1987, p. 177–180
    7. 7)
      • Iterative and sequential kalman filter-based speech enhancement algorithms
    8. 8)
      • Time–domain approach using multiple kalman filters and EM algorithm to speech enhancement with nonstationary noise
    9. 9)
      • Wavelet speech enhancement based on the teager energy operator
    10. 10)
      • Speech enhancement based on wavelet thresholding the multitaper spectrum
    11. 11)
      • Noisy speech enhancement using discrete cosine transform
    12. 12)
      • Soft thresholding for DCT speech enhancement
    13. 13)
      • A subspace approach for enhancing speech corrupted by colored noise
    14. 14)
      • A signal subspace approach for speech enhancement
    15. 15)
      • An adaptive KLT approach for speech enhancement
    16. 16)
      • Signal/noise KLT based approach for enhancing speech degraded by colored noise
    17. 17)
      • On the application of hidden Markov models for enhancing noisy speech
    18. 18)
      • A Bayesian estimation approach for speech enhancement using hidden Markov models
    19. 19)
      • Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator
    20. 20)
      • A parametric formulation of the generalized spectral subtraction method
    21. 21)
      • Suppression of additive noise using a power spectral density MMSE estimator
    22. 22)
      • Speech enhancement based on audible noise suppression
    23. 23)
      • Single channel speech enhancement based on masking properties of thehuman auditory system
    24. 24)
      • A perceptually motivated approach for speech enhancement
    25. 25)
      • Spectral subtraction using reduced delay convolution and adaptive averaging
    26. 26)
      • Noise suppression by spectral magnitude estimation-mechanism and theoretical limits
    27. 27)
      • The measurement of power spectra from the point of view of communications engineering
    28. 28)
      • Yang, W., Benbouchta, M., Yantorno, R.: `Performance of the modified bark spectral distortion as an objective speech quality measure', Proc. IEEE Int. Conf. ASSP, 1998, p. 541–544

Related content

This is a required field
Please enter a valid email address