A Graphical User Interface For Musical Audio Source Separation
暂无分享,去创建一个
There are several versions of the source separation program, with different fea-tures, notably: use of PyQt4 or PySide, and whether an estimation of themelody line is provided to the user, before she can choose/correct it.More specifically, there are 3 systems:• the original system that was used for the experiments of [DT2012]: use ofPyQt4, no estimation of the melody line,• a version of the PyQt4 program, with estimation of the melody line,• at last, a PySide version, with estimation of the melody line.Since the source code is provided, advanced users may modify these withminor changes to the code.In order to use the Python scripts, the following software/packages/modulesare needed:• Qt (version 4.7, qt.nokia.com, included in PyQt4 binaries, see below)• Python (version 2.7, use EPD: http://www.enthought.com/products/epd.php)• Numpy (version 1.6+, included in EPD)1
[1] Gaël Richard,et al. A Musically Motivated Mid-Level Representation for Pitch Estimation and Musical Audio Source Separation , 2011, IEEE Journal of Selected Topics in Signal Processing.
[2] Gaël Richard,et al. Source/Filter Model for Unsupervised Main Melody Extraction From Polyphonic Audio Signals , 2010, IEEE Transactions on Audio, Speech, and Language Processing.
[3] Jean-Philippe Thiran,et al. Musical Audio Source Separation Based on User-Selected F0 Track , 2012, LVA/ICA.