— Humpty Dumpty, Through the Looking-Glass
by Lewis Carroll, 1872
This question intrigued a lot of my researchers in recent years. In the following I summarise my view and point to some of our recent work. Read More
My main research interest is Semantic Audio, an interdisciplinary field in the confluence of Digital Signal Processing, Machine Learning including Deep Learning, and various knowledge representation and knowledge sharing technologies such as Semantic Web Ontologies, Linked-data, knowledge-based reasoning and the Semantic Web. I'm interested in extracting, analysing and linking data about music and developing applications that use semantic metadata, bringing the power of semantic technologies to music technology. Read More
in collaboration with Music Hackspace and with partners MuseHub and The Audio Programmer. Over 12 apps were submitted from 70+ participants, including students from QMUL's Sound and Music Computing (SMC MSc) masters programme. I have two PhD topics one is with industry funding within the AIM CDT listed here. Additional topics of interest can be found on my research page. successfully passed her viva. Her Thesis is titled: Learning Music Representations from Audio and Language. for our paper with PhD Student Elona Shatri titled Knowledge Discovery in Optical Music Recognition: Enhancing Information Retrieval with Instance Segmentation. for our paper with PhD Student Ilaria Manco titled MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models. successfully passed his viva. His Thesis is titled: Enveloping and Shaping the Sound: Analysis of the perception of retro aesthetics in popular music production. with Brecht De Man. The conference chaired by Prof. Josh Reiss will be held at QMUL between September 8-10, 2025. successfully passed her viva. Her Thesis is titled: Affective Live Coding: Fostering Human-Machine Collaboration with Autonomous Agents. which aims to create a platform for critical examination and exploration of the ethical dimensions of AI by engaging with scholars, researchers, and practitioners from different fields. titled Singing Voice Synthesis Using Differentiable LPC and Glottal-Flow-Inspired Wavetables. for our paper with Sound and Music Computing (SMC MSc) student Matthew Rice titled General Purpose Audio Effect Removal. successfully passed his viva. His Thesis is titled: Unveiling the Art of Piano Performance: A Study of Pianist Identification through Statistical and Hierarchical Models. for the project titled: ReVamp: Community Focused Software for Music and AI Research in collaboration with the BBC R&D and Steinberg Media Technologies. The project is looking to embed Sonic Visualiser into Digital Audio Workstations. . I'm a founding member and officer responsible for seminars. You can find more information at the IoS Research Network's homepage. for our paper with PhD Student Cyrus Vahidi titled Differentiable Time-Frequency Scattering on GPU. titled Ontology based Machine Learning in Semantic Audio Applications at at the International Semantic Intelligence Conference (ISIC 2021). I have several PhD topics listed here. Additional topics of interest can be found on my research page. . I'm editing this JAES Special Issue with Dr. Luca Turchet, Dr. Cristina Rottondi and Dr. Carlo Fischione. Submissions due 1 March 2021.. ISIC is an international platform for the Artificial Intelligence, Machine Learning and the Semantic Web communities. The conference will be held between 25-27 Feb. 2021 has been awarded her degree for her Thesis titled Intelligent Control of the Dynamic Range Compressor has successfully passed her PhD Viva. The Thesis is titled Digital collections of art: an investigation of engagement to support casual explorations. The workshop will be held in conjunction with the 27th IEEE FRUCT conference on 7-8 September 2020 in Trento, Italy. Papers due on 15 June 2020.. I'm editing this JWS Special Issue with Dr. Kevin Page. Submissions due 7th February 2020.. I'm editing this Special Issue with Dr. Leonardo Gabrielli and Dr. Juhan Nam. Submissions close on 31 July 2020. in collaboration with Steinberg Media Technologies within the AIM CDT our new Center for Doctoral Training in AI and Music.. My talk is titled Ontology Mediated Semantic Audio Services and Applications. has been evaluated Excellent during the final review meeting of the European Commission in Luxembourg. I have several PhD topics listed here.I'm one of the investigators of this programme which will fund over 72 PhD studentships (~12 PhD students per year for the following 5 years). AHRC grant funded with Nick Bryan-Kinns (PI), Johan Pauwels and Tongji University, Shanghai, China. Deadline: 7 Feb 2019 Music session, Hangzhou, China. AASP-L2: Sound event detection and classification. Call for Contributions released. I'm chairing ISAI18 in Bologna, Italy on 14-15 Nov. 2018. Submission deadline: 14 Sept. 2018. is now published. programme published. I'm co-chairing this workshop with Kevin Page (Oxford U.) and Sean Bechhofer (U. of Manchester) to be held at ISWC2018 on 9 Oct. in Monterey, California. is now published. Due to the large number of great papers we received, we are planning a second edition of the special issue to be completed soon.. This is an 8 month post in Semantic Audio (Audio Signal Processing and/or Music Information Retrieval with Linked Data and Semantic Web technologies) funded from my AudioCommons grant. Application deadline: 20 May 2018.in IEEE Transactions on Emerging Topics in Computational Intelligence (Volume: 2, Issue: 2, April 2018). to be held in conjunction with ISWC 2018 in October 2018. Paper submission deadline: 18 May, 2018. Submission via Easychair..
AIM CDTUKRI Centre for Doctoral Training in Artificial Intelligence and Music.
Read More
Re-VampCommunity focussed research software for music and audio
Read More
Industry PartnershipsSeveral industry collaborations totalling nearly £1m in funding.
Read More
IntelligentFXIntelligent Control of the Dynamic Range Compressor (IAA).
Read More
AudioCommonsThe Audio Commons Ecosystem facilitates using open sound content in professional contexts.
Read More
FAST-IMPACtFusing Audio and Semantic Technologies for Intelligent Music Production and Consumption
Read More
SAFESemantic Audio Feature Extraction in collaboration with DMT-Lab @BCU.
Read More
M4Making Musical Moods Metadata in collaboration with BBC & ILM. Music recommendation @BBC.
Read More You can find more up to date information on my
Linked-In page.
You can find some of my software and ontologies on C4DM's
Isophonics website which I help to maintain.
You can find some of my projects on
SoundSoftware.ac.uk.
ORCiD ID: 
orcid.org/0000-0003-2580-0007
Dr. George Fazekas, Senior Lecturer in Digital Media
Address: Centre for Digital Music,
Queen Mary University of London, Mile End Road, London E1 4NS
Email: george[dot]fazekas@qmul.ac.uk
SAWA-Feature Extractor
Moodplay and MyMoodply
SAWA-TempEst
VamPy
GratefulDeadLive
© Copyright 2025 George Fazekas.