About

Marsyas (Music Analysis, Retrieval and Synthesis for Audio Signals) is an open source software framework for audio processing with specific emphasis on Music Information Retrieval applications. It has been designed and written by George Tzanetakis (gtzan@cs.uvic.ca) with help from students and researchers from around the world. Marsyas has been used for a variety of projects in both academia and industry.

Featured Project

Modeling Emotional Content of Music

In this project, the emotional content of music was modeled as a function of music features. The model's inputs were time varying features; many features were extracted using Marsyas. The model's output was a 2-dimensional time varying signal that quanitified emotion. The emotion signal was generated by volunteers who evaluated the emotional content of several musical selections and models were created using system identification techniques. M. D Korhonen Systems Design Engineering, University of Waterloo, Ontario, Canada, 2004

Featured Developer

Coder Steven Ness

Affiliation : University of Victoria

Steven is a mad scientist and coder who works on various aspects of Marsyas. He added unit tests to Marsyas, turned the website into a Ruby on Rails backend, has written some Marsystems, and uses Marsyas in the development of rich internet-enabled applications like cantillion and pan.sness.net. He's currently doing his M.Sc. in the lab of George Tzanetakis in the field of Music Information Retrieval.

Featured Web Demo

Neil's Skookum MarSystem Network Constructor Neil's Skookum MarSystem Network Constructor

A Java web applet built with Processing that allows users to construct Marsyas networks inside a web browser.

Featured Video

Marsyas with open frameworks and fiducial tracking

MarMixer is an openFrameworks application to mix several sound sources (microphone and sound files) using Marsyas. Fiducial markers from the Reactable project are used to control the volume and pitch of each sound; moving the crossfader fiducial closer to an audio source increases its volume, and rotating the fiducial for each audio source changes the pitch.