Emerge Demo

From Emcap

1 Demo Emerge

[edit]

Demo Emerge

by Ricard Marxer <email@ricardmarxer.com>

Music Technology Group, Universitat Pompeu Fabra

2008/2/4

Download Emerge 1.0 (GNU/Linux)

Download Emerge 1.0 (Windows)

[edit]

What Is The Module?

This module is a graphical frontend to a pipeline using all the modules to create a model of human listening. Emerge is a research tool for the study of cognitive processes involved in the human music listening task. Emerge implements a system that integrates different computational models to mimic the processes happening in the human brain to during the exposure to music. The Emerge system has its main focus in emergent representations and active perception.

The system detects and extracts musical events by implementing an auditory model which is in charge of onset detection and feature extraction. The system then uses clustering techniques to create a symbolic representation for these events by emerging a taxonomy. Finally sequence learning models are used to find and describe frequent patterns and to fill or predict the nature and position of future or missing events.

The system works in an online and completely unsupervised manner. Emerging the internal representations of the outside world (the music it is exposed to) by using only the input data and no previous knowledge.

Emerge offers interactive visualization, sonification and control of the active models and the input and output data. Emerge is built on top of the python libraries Sepel and Ricaudio.

[edit]

What Are The Inputs/Outputs?

This module takes as input a filename of a WAV audio file. The output of the module is an interactive visualization and sonification control center where it shows the processes taking place in the several stages of the human listening model.

[edit]

What Are The Parameters?

There are no parameters currently in this demo.

[edit]

What Are The System Requirements?

[edit]

GNU/Linux

The package can be installed in several different ways, depending on your system. The easiest way is to install the setuptools package. On Debian based systems:

$ sudo apt-get install python-setuptools

and then just write the following:

$ sudo easy_install http://www.ricardmarxer.com/emcap/Emerge-1.0-py2.5.egg

If this method does not work correctly, one must install manually all the dependencies, and build the package himself. For the software to fully work you must have the following dependencies installed:

Python 2.5 or higher: http://www.python.org/download/
scipy 0.6.0 or higher: http://www.scipy.org/Download
numpy 1.0.4 or higher: http://numpy.scipy.org/
PyDispatcher 1.03 or higher: http://pydispatcher.sourceforge.net/ (must build and install manually)
scikits.audiolab: http://www.ar.media.kyoto-u.ac.jp/members/david/softwares/audiolab/#download-and-installation (must compile manually)
aubio: http://aubio.org/
Matplotlib 0.98.3 or higher: http://matplotlib.sourceforge.net/
PyQt 4.4 or higher: http://www.riverbankcomputing.co.uk/software/pyqt/download

Then one must download the package here and run:

$ python setup.py build
$ sudo python setup.py install

[edit]

Windows

A binary package has been made for ease of installation and use. To run, one must unzip the package somewhere and run the following executable:

emem-demo-emerge.exe

[edit]

How To Cite

@incollection{marx07,
 author = {Ricard Marxer and Piotr Holonowicz and Hendrik Purwins},
 title = {Dynamical Hierarchical Self-Organization of Harmonic, Motivic, and
 Pitch Categories},
 address = {Vancouver, Canada},
 booktitle = {Music, Brain and Cognition. Part 2: Models of Sound and
 Cognition, held at NIPS)},
 note = {(to appear)},
 year = {2007}
}

[edit]