Below we provide a list of git/mercurial/package repositories where we publish the code underlying the DML system. All code is hosted in mercurial repositories at code.soundsoftware.ac.uk under the GPLv3 license.
The cliopatria repository contains the implementation of the information and results management system and API. The source code can be found here:
hg clone https://code.soundsoftware.ac.uk/hg/dml-open-cliopatria.
The source for the DML Vis is hosted here:
hg clone https://code.soundsoftware.ac.uk/hg/dml-open-vis.
We welcome contributions towards the code. If you use the code for a scientific publication, you can cite [...]. Tools to work with the mercurial version control system are available at https://www.mercurial-scm.org/, with a GUI at EasyMercurial.
The ASyMMus project and its integration into the DML web interface were presented by Daniel Wolff during his departmental talk on music similarity.
From the abstract:
The concept of similarity can be applied to music in a multitude of ways. Applications include systems which provide similarity estimates depending on the specific user and context as well as analysis tools that show similarity of music with regards to specified compositional, physical or contextual features. The ASyMMuS project allows musicologists to apply similarity analysis to musical corpora on a big-data infrastructure – allowing for a comparison of e.g. the works of a certain composer.
Read here for more information and the full abstract.
The DML Vis interface is now available online. It enables you to explore, analyse and compare music collections and recordings from three large libraries originating from the British Library’s Sound Archives, CHARM and I Like Music.
We invite you to play with the interface: http://dml.city.ac.uk/vis/ and have a look at our introduction.
Furthermore we provide access to the analysis and features used in the DML interface via our ClioPatria service. Here you may browse the triplet store by predicates such as bl composer (e.g. for classical music) or subject which is suited well for ethnographic recordings. We are happy to receive feedback.
Several researchers from the ASyMMus and DML projects prominently contributed to the high-profile international workshop “Music Similarity: Concepts, Cognition and Computation“.
The workshop gathered experts on music similarity from Computer Science, Musicology, Music Psychology and related scientific fields. In a highly-motivated series of workgroups and talks, our researchers collaborated with other experts in the field in theoretical concepts and computer models of music similarity.
Main areas that were addressed :
* Relationship of similarity and categorisation
* Embedding similarity in context
* Perception and cognition of similarity
* Similarity modelling
* Similarity in music content – music analysis
* Similarity in music expression
Results include a roadmap for interdisciplinary music similarity research as well as future collaborations across scientific fields.
Try out the visualisation at: http://dml.city.ac.uk/chordseqvis/
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: http://dml.city.ac.uk/chordseqvis/!