THE AUDITORY MODELING TOOLBOX

Applies to version: 0.9.9

View the code

Go to function

may2011 - GMM-based estimation of azimuth direction for concurrent speakers

Usage

out = may2011(input,fs);

Input parameters

input binaural input signal [nSamples x 2 channels]
fs sampling frequency in Hertz

Output parameters

out
localization structure containing the following fields:

.param = processing parameters

.azFrames = frame-based azimuth estimate [Frames x 1]

.azimuth = time-frequency azimuth estimate [nFilter x nFrames]

.rangeAZ = azimuth grid [nAzDir x 1]

.prob = 3D probability map [nFilter x nFrames x nAzDir]

.loglik = 3D log-likelihood map [nFilter x nFrames x nAzDir]

.itd = interaural time difference [nFilter x nFrames]

.ild = interaural level difference [nFilter x nFrames]

.ic = interaural coherence [nFilter x nFrames]

References:

T. May, S. van de Par, and A. Kohlrausch. A probabilistic model for robust localization based on a binaural auditory front-end. IEEE Trans Audio Speech Lang Proc, 19:1-13, 2011.