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

ORBIT Project (BBC Research)

ORBIT - “Object Re-configurable Broadcast Infrastructure Trial”, a contract pilot project between the BBC R&D (http://www.bbc.co.uk/rd/index.shtml) and INESC Porto (http://www.inescporto.pt): development of automatic audio segmentation and classification tools using Marsyas (September 2001 ~ September 2002).

Featured Developer

Coder and Code Styler Stefaan Lippens

Affiliation : Ghent University, Belgium

My first encounter with Marsyas was in 2002. It was used for my master thesis at Ghent University on the topic of automatic musical genre classification. After completing my electrical engineering studies, I started working in the field of image processing and obtained my PhD on halftoning and printing. Since 2008 I'm back in the field of audio and music processing, now as a post-doctoral researcher at the Digital Speech and Signal Processing research group of Ghent University. The research revolves around music information retrieval and is bridged with an outside company. Together we focus on large scale automatic extraction of several music characteristics such as musical genre and rhythm style. My main Marsyas activities and contributions are situated in the core MarSystems and the Python bindings.

Featured Web Demo

MarGrid Tags MarGrid Tags

MarGrid Tags is a Flash based web application that allows users to interactively browse a two-dimensional representation of different collections of music. The 2D representations are generated using a Self-Organizing Map (SOM) which maps a high dimensional feature space to two dimensions. Both the feature extraction and SOM algorithm are calculated using Marsyas.

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