Prof Mark Plumbley
Title: Director of Centre for Digital Music
Professor of Machine Learning and Signal Processing
Tel: National: 020 7882 7518
International: +44 20 7882 7518
Fax: National: 020 7882 7997
International: +44 20 7882 7997
Office: Eng. 111
Research Group: Centre for Digital Music
- 29 May 2013: Come to our ICASSP 2013 Special Session on "Acoustic Event Detection and Scene Analysis" [SS-L4, Wed May 29, 15:20-17:20, Room 121/122]
- 27-31 May 2013: See you at ICASSP 2013, Vancouver. Papers:
- Mailhé, Sturm & Plumbley: Behavior of greedy sparse representation algorithms on nested supports. [Session SPTM-P2.14, Tue May 28, 10:50-12:50]
- O'Hanlon & Plumbley: Automatic music transcription using row weighted decompositions. [Session AASP-L1.4, Tue May 28, 11:50 - 12:10]
- Stowell, Muševič, Bonada & Plumbley: Improved multiple birdsong tracking with distribution derivative method and Markov renewal process clustering. [Session AASP-P5.4 Wed May 29, 10:30-12:30]
- Giannoulis, Klapuri & Plumbley: Recognition of harmonic sounds in polyphonic audio using a missing feature approach. [Special Session SS-L4.1, Wed May 29, 15:20 - 15:40]
- Fritsch & Plumbley: Score informed audio source separation using constrained nonnegative matrix factorization and score synthesis. [Session AASP-P11.9, Fri May 31, 15:20-17:20]
- Postdoctoral Research Assistant: Acoustic Analysis Tools for Sound Archives [Deadline: 30 Dec 2012]
- 18 Dec 2012: Presenting at DMRN+7: Digital Music Research Network One-day Workshop, QMUL, London, UK
- 17 Dec 2012: Presenting tutorial at 9th IMA International Conference on Mathematics in Signal Processing, Birmingham, UK [slides]
- 3-7 Dec 2012: Invited talk at ESI12 Workshop on Time-frequency methods for the applied sciences, Vienna, Austria
- 1 Jun 2012: At Digital Shoreditch 2012: Summit
- 28 May 2012: At EPSRC Developing Leaders: Inspirations Event
- 22 May 2012: At Digital Shoreditch 2012: Innovate.
- 18 May 2012: At British and Irish Sound Archives' Annual Conference (2012 BISA Day), Norwich, UK.
- 1 Apr 2012: Invited talk at CREST Symposium on Human-Harmonized Information Technology, Kyoto, Japan (after ICASSP).
- 31 Mar 2012: Talk at VERSAMUS 2012 Workshop on Advances in Music Signal And Information Processing, Tokyo, Japan, 31 Mar 2012.
- 25-30 Mar 2012: At ICASSP 2012, Kyoto. Papers:
- Mailhe / Barchiesi / Plumbley: INK-SVD: Learning incoherent dictionaries for sparse representations
- Cannam / Figueira / Plumbley: Sound software: Towards software reuse in audio and music research
- Cleju /Jafari / Plumbley: Analysis-based sparse reconstruction with synthesis-based solvers (in our Special Session on Analysis Sparsity)
- Fujihara / Klapuri / Plumbley: Instrumentation-based music similarity using sparse representations
- O'Hanlon / Nagano / Plumbley: Structured sparsity for automatic music transcription
- 12-15 Mar 2012: At LVA/ICA 2012, Tel Aviv. Papers:
- Gretsistas / Plumbley: Group Polytope Faces Pursuit for recovery of block-sparse signals
- Mailhe / Plumbley: Dictionary Learning with Large Step Gradient Descent for Sparse Representations
- 27 Feb 2012: Invited talk on "Sound recognition technologies" at International Workshop on Digital Media Analysis, Search and Management (DMASM 2012), San Diego, CA (via videolink).
- 20-21 Feb 2012: At the SCANDLE workshop "Making Sense of Sounds" in Plymouth.
- 8-9 Feb 2012: Meeting of new Danish Strategic Research project CoSound.
- 31 Jan 2012: At workshop on "The separation of envelope and fine-structure for auditory research", CNBH, Cambridge
- 23/24 Jan 2012: At EPSRC Digital Economy workshops on "New economic models" and "IT as a utility"
- 5 Jan 2012: At initial meeting of the "Creativeworks London" AHRC Knowledge Exchange Hub, leading the Digital Economy research cluster.
- 20 Dec 2011: At C4DM-hosted DMRN+6: Digital Music Research Network One-day Workshop
- 19 Dec 2011: New Danish grant: CoSound – A Cognitive Systems Approach to Enriched and Actionable Information from Audio Streams, led by Jan Larsen at DTU
- 29 Nov 2011: At EPSRC ICT Perspectives / Networks of Networks discussion meeting.
- 8 Nov 2011: C4DM presenting our "Cutting Edge Research" at AES UK event in London.
- 24-28 Oct 2011: At ISMIR 2011, Miami. Peter Foster and Anssi Klapuri presenting our poster on Causal prediction of continuous-valued music features.
- 20-21 Oct 2011: Visiting MERL, MIT Media Lab and The Echonest in Boston between WASPAA and ISMIR.
- 16-19 Oct 2011: At WASPAA 2011, New Paltz. Dimitrios Giannoulis and Daniele Barchiesi presenting our paper on Disjointess of Sources in Music.
- 15 Sep 2011: ICASSP 2012 Special Session on "Analysis Sparsity" accepted - see you in Kyoto in March!
- 14 Sep 2011: Samer Abdallah and Henrik Ekeus at British Science Festival with installation based on IDyOM project [news item].
- 14 Sep 2011: Join us for Centre for Digital Music: Past, Present and Future and Shaping the Future: Business/Research Collaboration in Digital Music, to celebrate 10 years of Digital Music research at Queen Mary!
- 1 Sep 2011: Invited talk on Analysing Digital Music at International Conference on Interdisciplinary Musicology (CIM11), Glasgow, Scotland.
- 16 Aug 2011: C4DM is part of £4m Knowledge Exchange Hub to benefit London’s creative economy. I'll be leading a part of this on "London's Digital Economy"
- 5 Aug 2011: 'Atmospheric Railway' by Di Mainstone and Adam Stark, at ReAnimate at the National Portrait Gallery. Reviewed in NewScientist Culture Lab and The Arts Desk
- 8 Jul 2011: At BBC MediaCityUK, Salford, for the launch of the new BBC Audio Research Partnership.
- 27-30 Jun 2011: At SPARS11 in Edinburgh. Includes presentations from PhD students Aris Gretsistas & Ken O'Hanlon, and postdocs Boris Mailhé & Ivan Damnjanovic.
- 2 Jun 2011: Press Release: New sound synchronisation technology holds the key to earlier diagnosis of heart disease [and at EPSRC]. See also DigiScope website.
Featured by: Electronics Weekly, ScienceDaily, e-Health Insider, The Engineer, Medical Xpress, e! Science News, Armenian Medical Network, Compute Scotland, Science Codex, My Health News, NewsODrome, Medical News Today, redOrbit (+ via wn.com, Yahoo News), Affective.com, Isaude.net,EureakAlert, Science2day, WebWire, MassDevice, Total Health, TopNews (NZ), HealthCanal, Health Jockey, Churnalism.com, Medical Daily, Medical Device Guru, biocompare, WellSphere, Polinema, Med Today, FirstScience.com, Sciencely.com, University of Porto Newsletter (in Portuguese), HospiMedica.
(Also some oddly reworded?: BreakingNews, asbigo)
- 25 May 2011: Co-chairing ICASSP 2011 Special Session: SS-L4: Learning Low-Dimensional Models for Large-Scale Data
- 23-27 May 2011: At ICASSP 2011, Prague. Papers:
- Hedayioglu / Jafari / Mattos / Plumbley / Coimbra: Separating Sources from Sequentially Acquired Mixtures of Heart Signals
- Barchiesi / Plumbley: Dictionary learning of Convolved Signals
- Adler / Emiya / Jafari / Elad / Gribonval / Plumbley: A Constrained Matching Pursuit Approach to Audio Declipping
- 20 May 2011: At EPSRC discussion on "Bringing together networks in ICT"
- 13-16 May 2011: At 130th AES Convention, London
- 12 May 2011: At MusicNet Music Linked Data Workshop
- 6 May 2011: See us at the Digital Shoreditch Summit
- 5-7 May 2011: See our research at the qMedia Open Studio
- 11-14 Apr 2011: Workshop and review for SMALL project in Paris
- 5 Apr 2011: See you at our EECS Research Open Day!
- 8 Mar 2011: Gave my Inaugural Lecture: Making Sense of Sound and Music
- 28 Feb - 1 Mar 2011: At DMASM 2011 International Workshop11 International Workshop in UCSD/Calit2, San Diego.
- 18 Feb 2011: At the Digital Communications KTN Personalised Interactive Broadcasting Event here at Queen Mary.
- 16 Feb 2011: Talking about research networking at EPSRC Workshop: Future Research Leaders in ICT
- 6-7 Jan 2011: Hosted SMALL Workshop on Sparse Dictionary Learning with Maria Jafari
- Tue 21 Dec 2010: At C4DM-hosted DMRN+5: Digital Music Research Network One-day Workshop
- Mon 20 Dec 2010: Hosted Machine Listening Workshop 2010 with Matthew Davies (despite the snow!)
Current Research Staff & Students
|Dr Samer Abdallah||RA: Information and Neural Dynamics of Music (IDyOM-2)|
|Constantin Barabasa||Assoc RS: Sparse representations|
|Daniele Barchiesi||RS: Audio source separation using sparse representations|
|Chris Cannam||RA: Sustainable Software for Audio & Music Research|
|Nicolae Cleju||Assoc RS: Sparse representations|
|Henrik Ekeus||RS: Models of perception and cognition in the artistic design process.|
|Luís Figueira||RA: Sustainable Software for Audio & Music Research|
|Aris Gretsistas||RS: Compressed Sensing of Audio Scenes|
|Fabio Hedayioglu||Assoc RS: Heart sound separation|
|Dr Maria Jafari||RA: Advanced Subband Systems for Audio Source Separation and RA: SMALL|
|Hassan Khalil||RS: Audio source separation|
|Shengchen Li||RS: Analysis of musical expression|
|Boris Mailhe||RA: Machine Listening using Sparse Representations|
|Tim Murray Browne||RS: Automated composition|
|Ken O'Hanlon||RS: Audio-visual analysis|
|Dr Andrew Robertson||RAEng/EPSRC Fellow: Intelligent Interactive Musical Performance Systems|
|Mehdi Shokri Zadeh||RS: Real-time audio source separation|
Recent Research Staff & Students
|Dr Samer Abdallah||RS: Towards Music Perception by Redundancy Reduction and Unsupervised Learning in Probabilistic Models, and RA: Information Dynamics of Music|
|Marco Bevilacqua||Assoc RS: Sparse Representations and Compressive Sensing|
|Dr Paul Brossier||RS: Real-Time Object-Based Coding|
|Dr Ivan Damnjanovic||RA: Sparse Models, Algorithms, and Learning for Large-scale data (SMALL) / SoundSoftware.ac.uk|
|Dr Matthew Davies||RA: Sparse Models, Algorithms, and Learning for Large-scale data (SMALL)|
|Jason Hockman||Assoc RS: Audio Rhythm Analsys|
|Dr Ian Johnson||RS: Regular language processing using neural networks|
|Jens Klingseisen||Assoc RS: Music analysis using Multiple-Cause Models|
|Antoine Movschin||Assoc RS: Artist identification|
|Dr Andrew Nesbit||RA: Sound Source Separation for Music Remixing and RA: Machine Listening using Sparse Representations|
|Andrew Robertson||RS: Interactive Real-time Musical Systems|
|Adam Stark||RS: Musical Audio Analysis for Real-Time Interaction|
|Dan Stowell||RS: Real-Time Analysis of Voice for Musical Applications|
|Keisuke Toyama||MSc by Research: Blind Source Separation|
|Dr Emmanuel Vincent||RA: Object-Based Coding of Musical Audio|
|Dr Beiming Wang||RS: Musical Audio Stream Separation|
|Steve Welburn||RS: Sparse Object-Based Coding of Music|
Current & Recent Research Funding
- Sustainable Software for Digital Music and Audio Research (EPSRC Grant EP/H043101/1, £947,057, 2010-2014), with Mark Sandler and others in the Centre for Digital Music.
- Information and Neural Dynamics in the Perception of Musical Structure (EPSRC Grant EP/H013059/1, £1,049,131 total, £286,079 to Queen Mary, 2010-2012), with Mark Sander and Samer Abdallah at Queen Mary; Geraint Wiggins, Joydeep Bhattacharya, Keith Potter and Marcus Pearce at Goldsmiths, University of London.
- Sparse Models, Algorithms and Learning for Large Scale Data (SMALL) (EU FET-Open Project FP7-ICT-225913, Total €1.9m, £249k to Queen Mary, 2009-2012). Partners: INRIA/IRISA (France), Univ of Edinburgh (UK), EPFL (Switzerland), Technion (Israel).
- Doctoral Training Centre in Digital Music and Media for the Creative Economy [Media and Ars Technology] (EPSRC Grant EP/G03723X/1, £5,923,383, 2009-2017), with Mark Sandler and Pat Healey.
- Machine Listening using Sparse Representations (EPSRC Leadership Fellowship EP/G007144/1, £1,236,776, 2008-2013).
- Platform Grant: Centre for Digital Music (EPSRC Grant EP/E045235/1, £1,057,355, 2007-2012), with Josh Reiss, Mark Sandler, Pat Healey and Nick Bryan-Kinns.
- OMRAS2: A Distributed Research Environment for Music Informatics and Computational Musicology (EPSRC Grant EP/E017614/1, £2.5m fEC, £1,451,161 to Queen Mary, 2007-2010), with Mark Sandler, Simon Dixon and Samer Abdallah at Queen Mary; Michael Casey and Tim Crawford at Goldsmiths, University of London.
- EASAIER: Enabling Access to Sound Archives through Integration, Enrichment and Retrieval (EU Project FP6-IST-033902, 2006-2009) with Josh Reiss at Queen Mary, and 6 other partners.
- Estimation of Melody from Audio using Harmonic and Rhythmic Information (Royal Society International Incoming Short Visit, £3,253, Oct-Nov 2005) with Juan Bello at Queen Mary and Dr Matija Marolt, University of Ljubljana, Slovenia.
- Sparse Representations for Signal Processing and Coding (EPSRC Grant EP/D000246/1, £282,902, 2005-2008), with Mike Davies.
- ICA Research Network, ICArn.org [Blind Source Separation and Independent Component Analysis Network] (EPSRC Grant EP/C005554/1, £62,058, 2005-2008), with Mike Davies at Queen Mary, plus 44 other researchers at 26 other UK institutions.
- Object-based Coding of Musical Audio (EPSRC Grant GR/S75802/01, £202,353 , 2004-2007), with Mark Sandler and Mike Davies. EPSRC Final Assessment: Outstanding.
- Techniques and Algorithms for Understanding the Information Dynamics of Music (EPSRC Grant GR/S82213/01, £184,965 to Queen Mary, 2005-2008), with Mark Sandler at QM, Geraint Wiggins and Michael Casey at Goldsmiths College, London.
- Digital Music Research Network [dmrn.org]. (EPSRC Grant GR/R64810/01, "Music Processing Network" £61,794, 2003-2005), with Mike Davies and Mark Sandler at Queen Mary, plus researchers at six other UK institutions. EPSRC Final Assessment: Outstanding.
- Information and noise in ICA for music (Leverhulme Trust Study Abroad Fellowship RF&G/10214: £12,020, April-July 2002). Three month visit to Helsinki University of Technology.
- Automatic Polyphonic Music Transcription Using Multiple Cause Models and Independent Component Analysis (EPSRC Grant GR/R54620/01, £124,946, 2002-2004), with Mike Davies and Mark Sandler. EPSRC Final Assessment: Outstanding.
- Advanced Subband Systems for Audio Source Separation (EPSRC Grant GR/S85900/01, £176,431, 2004-2007), with Mike Davies and Mark Sandler.
- SIMAC: Semantic Interaction with Music Audio Contents (EU Grant FP6-IST-507142, €2,982,921 total, £219,000 to Queen Mary, 2004-2006), with Mark Sandler at Queen Mary. Partners: UPF (Spain), ÖFAI (Austria), Matrix Data (UK), Philips Research (Netherlands).
Following my graduation in 1984 (Electrical Sciences Tripos, Churchill College, Cambridge), I joined Thorn-EMI Central Research Laboratories, working on videotape data storage and high-definition TV. In 1987 I returned to Cambridge University Engineering Department as a Research Student under the late Frank Fallside, working on information theory and neural networks, continuing as a Research Associate. In 1991 I joined the Centre for Neural Networks at King's College London, initially in the Department of Mathematics and then Computer Science before moving to Electronic Engineering 1995. I was Joint Coordinator of the the EC-funded NEuroNet Network of Excellence in Neural Networks.
I have been working in source separation and independent component analysis (ICA) for 5 years, following a background in neural networks since 1987, including the particular method of non-negative ICA. I have applied ICA and related models to the analysis of music, including automatic music transcription. In 2002 I joined the new Digital Signal Processing group at Queen Mary, University of London, and later that year visited the ICA group at Helsinki University of Technology on a 3-month Leverhulme Trust Study Abroad Fellowship. Recent EPSRC Funding includes: Automatic Polyphonic Music Transcription Using Multiple Cause Models and Independent Component Analysis (GR/R54620/01); Object-based Coding of Musical Audio (GR/S75802/01); Information Dynamics of Music (GR/S82213/01). I currently coordinate the EPSRC Digital Music Research Network (GR/R64810/01) and the ICA Research Network (EP/C005554/1).
In my spare time I dabble in website construction, including helping out on PostgraduateStudentships.co.uk, a website to help students find funding for Masters and PhD study.