Description: Matlab implementation of an MMSE based noise PSD tracking algorithm for speech enhancement. This package is an implementation of the algorithm described in "MMSE BASED NOISE PSD TRACKING WITH LOW COMPLEXITY", by Richard C. Hendriks, Richard Heusdens and Jesper Jensen, IEEE International Conference on Acoustics, Speech and Signal Processing, 03/2010, Dallas, TX, p.4266-4269, (2010).
The algorithm has rather low complexity, but is able to accurately estimate the noise PSD for non-stationary noise with rather low tracking delay.
File list (Check if you may need any files):
TabGenGam
.........\ConflHyperGeomFun.m
.........\ei.m
.........\logMMSEsupergaus.m
.........\lookup_gain_in_table.m
.........\ParCylFun.m
.........\readme.txt
.........\TabulateGainGamma1.m
.........\TabulateGainGamma2.m
.........\TabulateGenGam1dft.m
.........\TabulateGenGam2dft.m
.........\Tabulate_gain_functions.m
estimate_snrs.m
estimate_snrs_bias.m
hendriks2010.pdf
init_noise_tracker_ideal_vad.m
license.txt
noise_psd_tracker.m
noise_psdest.m
Download