- Title: Music Informatics: Measuring and Modelling Music
- Speaker: Simon Dixon (QMUL)
- Time and date: 1pm to 2pm, October 6th, 2021 (Wednesday)
- Room: Virtual (Zoom)
The Game AI Research Group is glad to announce a (virtual) talk by Simon Dixon on Wednesday Oct 06 2021 at 13:00.
All welcome (especially students), no pre-booking required
Abstract
Over the past two decades, the field of music informatics (or music information retrieval/research, MIR) has grown from a small number of individual researchers to a large international community with strong industry involvement. At the beginning of the millennium, data was scarce, methods were ad hoc, and there were no standard methodologies or datasets for comparing competing approaches. The next decade saw definition of standard tasks such as beat-tracking, cover-song detection and automatic transcription, development of various approaches mainly based on signal-processing, and the release of benchmark datasets for testing and comparing alternative solutions. The most recent decade has been dominated by deep learning, as in many other fields. In my talk, I will discuss a number of MIR tasks that I have contributed to: beat tracking (2001), audio alignment (2005), automatic transcription of music (2012, 2016), analysis of melodic patterns in jazz improvisation (2019), cover song detection (2021) and lyrics transcription (2021). I will conclude with some thoughts on possible relationships between music and games research.
Bio
Prof. Simon Dixon is Director of the UKRI Centre for Doctoral Training in Artificial Intelligence & Music (2019-2027), Coordinator of the EU H2020 Innovative Training Network: New Frontiers in Music Information Processing (2018-2022), and Deputy Director of the Centre for Digital Music (2015-) at Queen Mary University of London. He has a PhD in Computer Science and LMusA diploma in Classical Guitar. He has over 20 years of research experience and has published over 200 papers in the area of music informatics, including work on high-level music signal analysis, computational modelling of musical knowledge and the study of musical performance. He was President of the International Society for Music Information Retrieval (ISMIR), is founding Editor-in-Chief of the Transactions of ISMIR, and member of the EPSRC Peer Review College. He has been PI on grants from UKRI (EPSRC, ESRC, AHRC), the European Commission (H2020, FP7), JISC, the TSB (now Innovate UK), and industry-funded projects.