论文信息 - Post-processing in masking-based β-order MMSE speech enhancement

Post-processing in masking-based β-order MMSE speech enhancement

Abstract A post-processing technique for improving the performance of the masking-based β-order MMSE method in speech enhancement is proposed in this letter. After the enhancement process, weak spectral components in the high-frequency band are usually over-attenuated. A non-linear high-frequency regeneration technique is used to re-synthesize the upper-band signal based on the lower-band speech.

Soo Ngee Koh | Ing Yann Soon | Xinxin Zhang | Changhuai You

[1] Susanto Rahardja,et al. /spl beta/-order MMSE spectral amplitude estimation for speech enhancement , 2005, IEEE Transactions on Speech and Audio Processing.

[2] David Malah,et al. Speech enhancement using a minimum mean-square error log-spectral amplitude estimator , 1984, IEEE Trans. Acoust. Speech Signal Process..

[3] Soo Ngee Koh,et al. Transformation of narrowband speech into wideband speech with aid of zero crossings rate , 2002 .

[4] Susanto Rahardja,et al. Masking-based beta-order MMSE speech enhancement , 2006, Speech Commun..

[5] Ephraim. Speech enhancement using a minimum mean square error short-time spectral amplitude estimator , 1984 .

[6] T. SOMERVILLE,et al. Applied Acoustics , 1958, Nature.

[7] Philipos C. Loizou,et al. Speech enhancement based on perceptually motivated bayesian estimators of the magnitude spectrum , 2005, IEEE Transactions on Speech and Audio Processing.