This letter proposes a noise spectrum estimation algorithm for speech enhancement. The algorithm incorporates the speech presence probability, which is calculated from SNR (signal-to-noise ratio) discrepancy. The discrepancy is measured based on the estimation of the a priori and a posteriori SNR. The proposed algorithm is found to be effective in rapidly switched noise environments. This is confirmed by the experimental results which indicate that the proposed algorithm when integrated in a speech enhancement scheme performs better than conventional noise estimation algorithms.
Atanu SAHA
Saitama University
Tetsuya SHIMAMURA
Saitama University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Atanu SAHA, Tetsuya SHIMAMURA, "Noise Spectrum Estimation Based on SNR Discrepancy for Speech Enhancement" in IEICE TRANSACTIONS on Information,
vol. E97-D, no. 2, pp. 373-377, February 2014, doi: 10.1587/transinf.E97.D.373.
Abstract: This letter proposes a noise spectrum estimation algorithm for speech enhancement. The algorithm incorporates the speech presence probability, which is calculated from SNR (signal-to-noise ratio) discrepancy. The discrepancy is measured based on the estimation of the a priori and a posteriori SNR. The proposed algorithm is found to be effective in rapidly switched noise environments. This is confirmed by the experimental results which indicate that the proposed algorithm when integrated in a speech enhancement scheme performs better than conventional noise estimation algorithms.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E97.D.373/_p
Copy
@ARTICLE{e97-d_2_373,
author={Atanu SAHA, Tetsuya SHIMAMURA, },
journal={IEICE TRANSACTIONS on Information},
title={Noise Spectrum Estimation Based on SNR Discrepancy for Speech Enhancement},
year={2014},
volume={E97-D},
number={2},
pages={373-377},
abstract={This letter proposes a noise spectrum estimation algorithm for speech enhancement. The algorithm incorporates the speech presence probability, which is calculated from SNR (signal-to-noise ratio) discrepancy. The discrepancy is measured based on the estimation of the a priori and a posteriori SNR. The proposed algorithm is found to be effective in rapidly switched noise environments. This is confirmed by the experimental results which indicate that the proposed algorithm when integrated in a speech enhancement scheme performs better than conventional noise estimation algorithms.},
keywords={},
doi={10.1587/transinf.E97.D.373},
ISSN={1745-1361},
month={February},}
Copy
TY - JOUR
TI - Noise Spectrum Estimation Based on SNR Discrepancy for Speech Enhancement
T2 - IEICE TRANSACTIONS on Information
SP - 373
EP - 377
AU - Atanu SAHA
AU - Tetsuya SHIMAMURA
PY - 2014
DO - 10.1587/transinf.E97.D.373
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2014
AB - This letter proposes a noise spectrum estimation algorithm for speech enhancement. The algorithm incorporates the speech presence probability, which is calculated from SNR (signal-to-noise ratio) discrepancy. The discrepancy is measured based on the estimation of the a priori and a posteriori SNR. The proposed algorithm is found to be effective in rapidly switched noise environments. This is confirmed by the experimental results which indicate that the proposed algorithm when integrated in a speech enhancement scheme performs better than conventional noise estimation algorithms.
ER -