I'm Senior Lecturer (Associate Professor) in Digital Media at Queen Mary University of London, working at the Centre for Digital Music (C4DM), School of Electronic Engineering and Computer Science.
I received an MSc degree at Queen Mary University of London, and a subsequent PhD degree in 2012 at the same institution. My doctoral thesis titled “Semantic Audio Analysis—Utilities and Applications” describes novel applications of semantic audio analysis, Semantic Web technologies and ontology-based information management in Music Information Retrieval as well as in intelligent audio production tools.
My main research interest includes the development of semantic audio technologies and their applications to creative music production, ontology-based information management, audio signal processing and machine learning including Deep Learning, Semantic Web, linked data, and knowledge-based reasoning. I'm leading QMUL's team on the EU funded H2020 Research and Innovation project Audio Commons as QM's Principal Investigator and conduct research on the Fusing Semantic and Audio Technologies for Intelligent Music Production and Consumption (FAST) project. I developed online tools for semantic audio analysis which seamlessly integrate with Semantic Web technologies.
I proposed a novel automatic ontology generation system for web-based audio signal processing applications in collaborative work. I worked with BBC Research and Development to build mood-based music recommendation systems in the TSB funded Making Musical Mood Metadata project, and collaborated with researchers from the Finnish Centre of Excellence in Interdisciplinary Music Research on creating semantic mood models for music. I collaborated with the French vocal group VoXP to create the Mood Conductor system that enables audiences to interact with performers in live improvised music using a Psychological model of mood and mobile technology. I contributed to several work threads and work packages on Audio Commons and FAST. For more details on recent works see my research pages.
I was general chair of ACM (in-coop.) Audio Mostly 2017 conference and papers co-chair and led the local organising committee of the 53rd AES International conference on Semantic Audio, co-organised by Queen Mary University and the Fraunhofer Institute. I'm guest editor of the Journal of the Audio Eng. Soc. (JAES), for example, Special Issue on Participatory Sound And Music Interaction Using Semantic Audio (2018), and Special Issue on the Internet of Sounds (2020) as well as Special Issue of the Journal of Web Semantics (JWS) on Semantic Technologies in the Creative Industries and Applied Sciences Special Issue Deep Learning for Applications in Acoustics: Modeling, Synthesis, and Listening (2019). I am Co-Investigator of several collaborative research projects, and a member of the IEEE, AES, ACM and BCS. I'm also a member of the Audio Mostly steering committee and recepient of the AES citation award.
I authored/co-authored over 150 peer-reviewed papers in leading journals and conferences such as IEEE/ACM transactions, Journal of Web Semantics, Journal of New Music Research, ISMIR, ICASSP, ACM Multimedia and others, including an award winning ISMIR paper on transfer learning.