DML project at AES ‘Cutting Edge Research’ event

The DML project was presented at the event sponsored by the Audio Engineering Society, entitled “Cutting Edge Research – from City University and King’s College London”, which took place at City University on 14th October.

The event showcased cutting edge research from City University’s Music Informatics Research group and King’s College London’s Centre for Telecommunications Research. As part of the event, Tillman Weyde gave a talk on the group’s activities (including the DML project), and Dr Dan Tidhar presented the poster entitled “Big Data for Musicology and Music Retrieval”.

Demo: Large-Scale Visualisations of Chord Sequence Patterns

Try out the visualisation at:

In the Digital Music Lab project we work on the automatic analysis of large audio databases. As a part of this process we have extracted chord sequence patterns in over a million tracks from the “I Like Music” commercial music collection. To allow for visual analysis and exploration of this new derived data by experts, we have created visualisations that expose frequent patterns and structures.

The interface that we have created mostly represents root movement and chord qualities geometrically. We use two individually configurable views in parallel to encourage the comparison between different representations of a corpus highlighting complimentary musical aspects as well as to emphasizes differences between datasets, here representing different genres. We apply and adapt existing several visualisation techniques, such as:

  • linked grid
  • linked circular grid
  • origin-destination grid
  • parallel coordinate plot
  • chord-based tonnetz

Try out the visualisation at:!

DML project at DLfM 2014

Current progress on the DML project will be presented at the 1st International Digital Libraries for Musicology workshop (DLfM 2014). DLfM will take place on 12th September at City University London. Project-related papers are listed below (click titles to download):

ASyMMuS project started!

ASyMMuS (“An Integrated Audio-Symbolic Model of Music Similarity”) is an AHRC project funded under the Amplification Awards call of the Digital Transformations in the Arts and Humanities Theme. This project aims to apply the newly developed technological infrastructure from the Digital Music Lab project, to answer the musicological question what constitutes and contributes to similarity of music. The £77k project (AH/M002454/1) is being carried out collaboratively between City University London, University College London, and Lancaster University.

For more information on the project, please visit the ASyMMuS proejct pages.

DML project at ECDA 2014

Current progress on the DML project will be presented at the ‘Statistical Musicology’ session of the European Conference on Data Analysis (ECDA 2014). ECDA will take place on 2-4 July in Bremen, Germany. Project-related talks are listed below:

  • Dan Tidhar, Srikanth Cherla, Daniel Wolff, and Tillman Weyde, “An iterative learning approach to dataset demarcation in music analysis”
  • Tillman Weyde, Stephen Cottrell, Emmanouil Benetos, Daniel Wolff, Dan Tidhar, Jason Dykes, Mark Plumbley, Simon Dixon, Mathieu Barthet, Nicolas Gold, Samer Abdallah, and Mahendra Mahey, “Digital Music Lab – A Framework for Analysing Big Music Data”
  • Srikanth Cherla, Dan Tidhar, Artur d’Avlia Garcez, and Tillman Weyde, “Machine Learning for the Analysis of a Large Collection of Musical Scales”

Digital Music Lab Workshop on Analysing Big Music Data

Digital Music Lab 1st Workshop on Analysing Big Music Data
19 March 2014, 10:00 – 15:30
Room C343, Tait Building, Northampton Square Site
City University London

The Digital Music Lab project invites participants to attend the first workshop on analysing big music data.  The workshop is aimed to explore some dataset-specific aspects of the project as well as more general opportunities and challenges which are involved with big music data research. It will include presentations by the project’s official advisors, Prof. Frans Wiering, Dr. Renee Timmers, and Prof. Tim Crawford, and several other invited speakers. The workshop will also include an interactive part in which participants will have the opportunity to formulate and refine research questions relating to specific datasets which will be presented and characterised.

For more information on the workshop, including programme, registration, and venue information, please visit the workshop webpage.