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

Musicream

Musicream is a novel music playback interface that lets users unexpectedly come across musical pieces they like. It facilitates active, flexible, and unexpected browsing. For example, the "similarity-based" sticking function enables user to easily pick out and listen to similar pieces from a streaming "flow" of music. Marsyas is used to automatically extract a single feature vector that characterizes the content of a particular music piece. That vector is used for color visualization of the audio content as well as to support the "similarity-based" sticking function. Marsyas provided an easy way to extract audio content information and enabled us to concentrate on designing and developing the user interface. Masataka Goto Senior Research Scientist, AIST, Japan

Featured Developer

Author of the most complex MarSystem network Mathieu Lagrange

Affiliation : Associate Researcher at Telecom Paris

I am interested in auditory scene analysis for music streams understanding. For such a purpose, Marsyas as a valuable tool as it provides the user with an efficient, easy-to-install platform for processing various type of audio data. As the owner of the "Most complex Marsystem network" Award, I can say that even on challenging research tasks, Marsyas proved to be flexible and fun to use.

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

KeyBoard Controlled Assistive Music Browser

The goal of this project is to develop Assistive Music Browser Software that will enable users with severe disabilities to navigate through their own collections of music via a variety of input methods. We extract relevant features and analyze the audio data within a collection of music (of essentially unlimited size) and map the songs onto a 2-D space, called a self-organizing map, based on similarity. Continual audio feedback is provided to the user as they search their collection to aide in navigation and selection. http://www.canassist.ca