MMSE based noise PSD tracking with low complexity

Author

Hendriks, Richard C. ; Heusdens, Richard ; Jensen, Jesper

Author_Institution

Delft Univ. of Technol., Delft, Netherlands

fYear

2010

fDate

14-19 March 2010

Firstpage

4266

Lastpage

4269

Abstract

Most speech enhancement algorithms heavily depend on the noise power spectral density (PSD). Because this quantity is unknown in practice, estimation from the noisy data is necessary. We present a low complexity method for noise PSD estimation. The algorithm is based on a minimum mean-squared error estimator of the noise magnitude-squared DFT coefficients. Compared to minimum statistics based noise tracking, segmental SNR and PESQ are improved for non-stationary noise sources with 1 dB and 0.25 MOS points, respectively. Compared to recently published algorithms, similar good noise tracking performance is obtained, but at a computational complexity that is in the order of a factor 40 lower.

Keywords

computational complexity; error detection; least mean squares methods; noise; speech enhancement; MMSE based noise PSD tracking; PESQ; SNR segment; low complexity method; mean squared error estimation; noise magnitude squared DFT coefficient; noise power spectral density; noisy data; nonstationary noise source; speech enhancement algorithm; Additive noise; Computational complexity; Discrete Fourier transforms; Frequency; Hearing aids; Noise robustness; Random variables; Signal to noise ratio; Speech enhancement; Statistics; Noise PSD estimation; speech enhancement;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on

Conference_Location

Dallas, TX

ISSN

1520-6149

Print_ISBN

978-1-4244-4295-9

Electronic_ISBN

1520-6149

Type

conf

DOI

10.1109/ICASSP.2010.5495680

Filename

5495680