| EPSRC Reference: |
EP/N035321/1 |
| Title: |
Beyond Plagiarism in Melody (BPM) |
| Principal Investigator: |
Collins, Dr T |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Faculty of Technology |
| Organisation: |
De Montfort University |
| Scheme: |
First Grant - Revised 2009 |
| Starts: |
03 October 2016 |
Ends: |
02 July 2017 |
Value (£): |
100,651
|
| EPSRC Research Topic Classifications: |
| Digital Signal Processing |
Music & Acoustic Technology |
|
| EPSRC Industrial Sector Classifications: |
|
| Related Grants: |
|
| Panel History: |
| Panel Date | Panel Name | Outcome |
|
28 Apr 2016
|
EPSRC ICT Prioritisation Panel - Apr 2016
|
Announced
|
|
|
Summary on Grant Application Form |
This project will investigate the development of a system for producing music originality reports, analogous to Turnitin's originality checking and reporting for text documents. Potential users include record companies and academic institutions, who would check artist/student material for potential cases of music plagiarism. Furthermore, advertising companies, artists, and students may also use the software pre-emptively, to determine the degree to which their new composition is truly original. Shazam, the non-academic partner and commercially successful service for automatic music recognition, has existed since the early 2000s. Signal processing researchers working in academia and for companies such as Shazam have struggled to extend music recognition algorithms, however, to capture more abstract yet perceptually meaningful correspondences between music excerpts - correspondences which often apply in cases of music plagiarism.
The premise of our research is that the solution to automatic plagiarism detection lies not in focusing solely on audio signals, and that recent work from the psychological literature on symbolic music similarity and memory may provide fresh insights. This work involves an extant software package (called FANTASTIC) for extracting melodic features, which are used as the basis of a statistical model that is able to predict human memory for melodies in behavioural experiments. In collaboration with Shazam Entertainment Ltd., the academic partners will pursue the objective of extending these features so that they apply beyond melody-only material, to music where multiple notes may sound at a given time. The technique used to achieve this is known as symbolic fingerprinting, and consists of making comparisons between locally constrained note combinations. The features developed will be used to model behavioural data gathered in a listening experiment, and so will form the perceptual modelling basis for future automatic plagiarism detection technology in music (i.e. Turnitin for music). One of the outputs of the project will be an interactive, web-based prototype, demonstrating the generation of music originality reports. Academic beneficiaries include national and international researchers in the fields of music information retrieval, music psychology, and music theory. Beyond academia, the intended beneficiaries of the proposed research are the music industry (e.g., music publishers, record companies), music copyright professionals, advertising companies, academic institutions, artists, and students.
The proposed project has the potential to make significant advances to knowledge concerning perception of music similarity and plagiarism, to put these advances in the hands of beneficiaries for the first time, and to shed new light on the nature of musical creativity and originality.
|
|
Key Findings |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Potential use in non-academic contexts |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Impacts |
|
| Description |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk |
| Summary |
|
| Date Materialised |
|
|
|
|
Sectors submitted by the Researcher |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
| Project URL: |
|
| Further Information: |
|
| Organisation Website: |
http://www.dmu.ac.uk |