Music Informatics

With online music stores offering millions of songs to choose from, users need assistance. Using machine learning, ontologies and the semantic web, our research seeks to assist people in finding the music they want, whether it is by playing an example of something similar, humming, or musicological query (such as 12 Bar Blues in G, with guitar and no drums).

One of our major current projects is OMRAS2, a joint project with Goldsmiths, University of London, funded by EPSRC. In this project we are developing a framework for annotating and searching collections of both recorded music and digital score representations such as MIDI.

We have developed systems for automatic playlisting from personal collections (SoundBite), for looking inside the audio (Sonic Visualiser), for hardening/softening transients, and many others. We also regularly release some of our algorithms under Open Source licences, while maintaining a healthy portfolio of patents.

This area is led by Dr Simon Dixon. Projects in this area include:

• High Level Logical Music Descriptors for Automatic Music Classification, Retrieval and Knowledge Discovery
• Sonic Visualser
• Semantic Music Analysis for Intelligent Editing
• Linking music-related information and audio data
• Multi-Level Chord Representations and their Applications in Musicology
• Interactive Auralisation With Room Impulse Responses
• OMRAS2: A Distributed Research Environment for Music Informatics and Computational Musicology

PhD Study - interested in joining the team? We are currently accepting PhD applications.