Speech Enhancement Based on Generalized Minimum Mean Square Error Estimators and Masking Properties of the Auditory System

@article{Hansen2006SpeechEB,
  title={Speech Enhancement Based on Generalized Minimum Mean Square Error Estimators and Masking Properties of the Auditory System},
  author={John H. L. Hansen and V. Radhakrishnan and Kathryn Hoberg Arehart},
  journal={IEEE Transactions on Audio, Speech, and Language Processing},
  year={2006},
  volume={14},
  pages={2049-2063}
}
In this paper, the family of conditional minimum mean square error (MMSE) spectral estimators is studied which take on the form (E(XEalphap/|Xp + Dp|))1alpha/, where Xp is the clean speech spectrum, and Dp is the noise spectrum, resulting in a generalized MMSE estimator (GMMSE). The degree of noise suppression versus musical tone artifacts of these estimators is studied. The tradeoffs in selection of (alpha), across noise spectral structure and signal-to-noise ratio (SNR) level, are also… CONTINUE READING
Highly Cited
This paper has 44 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 31 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 35 references

Dual-channel speech enhancement with auditory spectrum based constraints

  • ——
  • Proc. IEEE ICASSP, Mar. 1992, pp. 297–300.
  • 1992
Highly Influential
7 Excerpts

Similar Papers

Loading similar papers…