RRP - Audio in-painting

This package requires the LTFAT and the GSPBox toolbox to be executed.


In this contribution, we present a method to compensate for long duration data gaps in audio signals, in particular music. To achieve this task, a similarity graph is constructed, based on a short-time Fourier analysis of reliable signal segments, e.g. the uncorrupted remainder of the music piece, and the temporal regions adjacent to the unreliable section of the signal. A suitable candidate segment is then selected through an optimization scheme and smoothly inserted into the gap.

In order to run this script you need to install the LTFAT and the GSPBox toolboxes. You can download them at:


A demo is availlable throught the file ai_demo_inpaint. The function ai_conf contains the default parameters.

Audio inpainting functions

For help, bug reports, suggestions etc. please send email to nathanael (dot) perraudin (at) epfl (dot) ch