Back to the audio resources page

original spectrum original spectrum

Unsupervised Spectral Subtraction Demo Page

This directory contains an example of the Unsupervised Spectral Subtraction scheme proposed in: "Unsupervised Spectral Subtraction", by G. Lathoud, M. Magimai.-Doss, B. Mesot and H. Bourlard, to appear in Proceedings of ASRU 2005.

Questions? ->

Note: a later version can cope with convolutive channels (telephone).

CONTENTS

More details on "apply_uss_to_wav.m"

The idea is to show the original magnitude spectrograms of a given WAV file, then to show how the ( Rayleigh + Shifted Erlang ) distribution is fitted, and finally the filtered magnitude spectrogram.

You can try it on various examples, stored in the DATA directory. The following MATLAB lines can be directly pasted onto a MATLAB interactive command-line.

Note: a strange looking fit in the "clean-NU-1028.streetaddr.wav" case is explained by some artificial data on silences in the waveform, most likely generated by the telephone speech/silence detector. This effect does not appear on all other files, and did not impact on the recognition performance in our experiments
Back to the audio resources page
Code and webpage by Guillaume Lathoud ( lathoud AT idiap DOT ch )
Last updated: 2006-12-22