email: me(at)benfields(dot)net

PhD

PhD Computer Science, April 2011
Goldsmiths, University of London

Thesis: Contextualize Your Listening: The Playlist as Recommendation Engine

available for download: pdf

MSc

M.S. Music Engineering Technology, May 2006

University of Miami

Thesis: On the Viability of Using Mixed Feature Extraction with Multiple Statistical Models to Categorize Music by Genre

available for download: pdf

BSc

B.S. Computer Engineering, March 2004
University of California, Santa Cruz
Senior Design Project: Securio - The Autonomous Home Security Robot, Audio Video Specialist

I currently split my time between two things. First, product work for In Our Cellar, a company I co-founded to create open data and web products for the beverage industry broadly and beer in particular. In my capacity there I'm particularly interested in improving the interaction model around point of sale in bars and pubs, through data mining, recommendation and excellent UX. The other half of my time is spent doing freelance consulting work. This takes many forms, from data model audits to full-stack web development. I prefer to work in python and know my way around javascript, ruby, and r. I'm a bit rusty, but can get by in java and C as well.

Research Interests

• Digitization of physical activity
• Music recommenders
• Metadata informed dynamics effects processing
• Human-like Playlist generation and playback (autoDJ)
• Song phrase segmentation
• Playlist (think DJ set, pod cast, etc.) segmentation

Program Committe Memberships/Reviewer

• ISMIR 2009 - 2013
• Workshop On Music Recommendation and Discovery (WOMRAD, in conjunction with ACM RecSys 2010)
• 2nd International Workshop on Advances in Music Information Research (AdMIRe, in conjunction with IEEE ICME)
• Musicae Scientiae

In Our Cellar Ltd.

• Co-Founder, Head of Product, January 2013 - Present
  Doing everything that needs to get done to help people drink better. Principally this involves fixing beer data on the Web, especially around point-of-sale availability. Current specific duties vary from full stack web development to data analytics to bizdev.

Independent Consulting

• mycricketaverage.com, June 2013
  Specification and development of twitter bot for tweeting relevant cricket statistics as part of promo.
• Ulyvox, January - May 2013
  Development of full web stack prototype for a social music sharing website.
• Audio Kicker, April - May 2010
  Development of prototypical backend, recommender and playlist engine

Musicmetric (Semetric Ltd.)

• Data Scientist/Analyst, April 2011 - January 2013
  Developed mechanisms for collection of data about Artists and other music entities across the internet. Created and tested novel algorithms for artist identification and recommendation systems.

University of Southampton

• Research Assistant, November 2010 - January 2011
  Short post on the Networked Environments for Musical Analysis grant, in the Intelligence, Agents and Multimedia group in the School of Electronics and Computer Science

Goldsmiths University of London, New Cross, London

• Research Assistant, September - October 2010
  Short post on the Networked Environments for Musical Analysis grant, in the Intelligent Sound and Music Systems Group within the Department of Computing
• Visiting Tutor, courses:
  • Creative Computing 2, Practice 2, Fall 2009
  • Creative Computing 3, Practice 3, Fall 2008
• Teaching Assistance, courses:
  • Computing 3, User Interface Design and Human Factors, Spring 2010

Gables Engineering, Coral Gables, FL

• Audio Systems Engineer Intern, June 2005 - January 2006.

University of Miami, Coral Gables, FL

• Ring Theater Venue Sound Designer, December 2004 - January 2006

Raytheon, San Diego, CA

• Student Intern, Summer 2004
• Student Intern, Summer 2001

University of California, Santa Cruz

• Modified Supplemental Instruction Leader, January 2003 - March 2004
• Porter College Technical Crew Manager -- Sound, March 2002 March 2004
• Porter College Technical Crew Member, January 2000 - March 2002

Publications

• A. Said, B. Fields, B. J. Jain, S. Albayrak, “User-Centric Evaluation of a K-Furthest Neighbor Col- laborative Filtering Recommender Algorithm”, in of Proc. of the 16th ACM Conference on Computer Supported Cooperative Work and Social Computing (CSCW’13), San Antonio, Texas, USA, February 2013.

• K. R. Page, B. Fields, D. De Roure, T. Crawford, J. S. Downie, “Reuse, Remix, Repeat: The Workflows of MIR”, in Proc. of Int. Symposium on Music Information Retrieval, Porto, Portugal, October 2012.

• D. DeRoure, K. Page, B. Fields, T. Crawford, I. Fujinaga, S. Downie, "An e-Research Approach to Web-Scale Music Analysis", Philosophical Transactions of the Royal Society A, 369(1949):3300-3317, 2011.

• B. Fields, K.Jacobson, C. Rhodes, M. d'Inverno, M. Sandler, M. Casey, "Analysis and Exploitation of Musician Social Networks for Recommendation and Discovery.", IEEE Transactions on Multimedia, 3(4):674-686, 2011.

• B. Fields, C. Rhodes, M. d'Inverno, "Automatic Group-Interactive Radio using Social-Networks of Musicians", in International AAAI Conference on Weblogs and Social Media (ICWSM), Barcelona, Spain, July 2011.

• B. Fields, K. Page, T. Crawford, D. De Roure, "The Segment Ontology: bridging music-generic and domain-specific", in Workshop on Advances in Music Information Research (AdMIRe), co-located the IEEE International Conference on Multimedia and Expo (ICME), Barcelona, Spain, July, 2011.

• K. Page, B. Fields, B. Nagel, G. O'Neill, D. De Roure and T. Crawford, "Semantics for music analysis through linked data: How country is my country?" in Proceedings of the International Conference on eScience, Brisbane, Australia, Dec, 2010.

• B. Fields, C. Rhodes, M. d'Inverno, "Using Song Social Tags and Topic Models to Describe and Compare Playlists." Workshop on Music Recommendation and Discovery, co-located with ACM Recommender Systems, Barcelona, September 2010.

• K. Jacobson, B. Fields, and M. Sandler, "Using audio analysis and network structure to identify communities of on-line social networks of artists," in Proc. of Int. Conference on Music Information Retrieval, Philadelphia, PA, USA, September 2008.

• B. Fields, K. Jacobson, C. Rhodes, and M. Casey, "Social playlists and bottleneck measurements: Exploiting musician social graphs using content-based dissimilarity and pairwise maximum flow values," in Proc. of Int. Symposium on Music Information Retrieval, Philadelphia, PA, USA, September 2008.

• B. Fields, K. Jacobson, M. Casey, and M. Sandler, "Do you sound like your friends? exploring artist similarity via artist social network relationships and audio signal processing," in Int. Computer Music Conference, August 2008.

• K. Jacobson, B. Fields, M. Sandler, M. Casey, "The Effects of Lossy Audio Encoding on Genre Classification Tasks," in Proc. Audio Engineering Society 124 Int. Conv., (Amsterdam, Netherlands), Audio Engineering Society, May 2008.

• B. Fields, M. Casey, "Using Audio Classifiers as a Mechanism for Content Based Song Similarity," in Proc. Audio Engineering Society 123 Int. Conv., (New York, NY, USA), Audio Engineering Society, October 2007

• M. Mauch, S. Dixon, C. Harte, B. Fields, M. Casey, "Discovering Chord Idioms through Beatles and Real Book Songs," in Proc. Int. Symposium on Music Information Retrieval, Vienna, Austria, Sept. 2007.

• B. Fields, “Using mixed feature extraction with multiple statistical models to achieve song categorization by genre,” in Proc. Audio Engineering Society 122nd Int. Conv., (Vienna, Austria), Audio Engineering Society, May 2007.

• B. Fields, “On the viability of using mixed feature extraction with multiple statistical models to achieve song categorization by genre,” Master’s thesis, University of Miami, Coral Gables, FL, May 2006.

Presentations and Talks

• Presentation: “Tastes Great, Less Wordy: Document NLP (For Beer)”, The Strange Loop, 18-20 September 2013 in St. Louis, MO, USA. upcoming.

• Presentation: “Should We Care About Content? Recommending by Proxy with Big Metadata”, O’Reilly Strata EU, 1 Octobrer 2012 in London, UK. slides.

• Presentation: “Customers Who Bought Music Also Bought Beer,” given at Devs Love Bacon, 13 April 2012 in London, UK. video.

• Tutorial: "Finding a Path Through the Juke Box: The Playlist Tutorial," given at ISMIR 2010, 9 August 2010 in Utrecht, The Netherlands. Co-presented with Paul Lamere. Slides as slideshare, pdf.

• Presenation: "Analysis and Exploitation of Musician Social Networks for Recommendation and Discovery," given at IEEE-THEMES, a workshop co-located at ICASSP 2010, 15 March 2010 in Dallas, TX, USA. Slides : Associated Journal Article

• Tutorial: "Mining the social web for music-related data," given at ISMIR 2009, 26 October 2009 in Kobe, Japan. Co-presented with Claudio Baccigalupo. Slides Resources

• Invited Talk: "The Semantic Web and Why You Should Care," given at JCDL 2009 Integrating Digital Library Content with Computational Tools and Services workshop, 19 June 2009 in Austin TX, USA. Co-presented with Kevin Page. Slides

Installations and Demonstrations

• K. Page, B. Fields, T. Crawford, D. De Roure, G. O'Neill and B. Nagel, "Semantics for Signal and Result Collections through Linked Data: How Country is my Country?," in International Conference on Music Information Retrieval, Utrecht, The Netherlands, Aug, 2010.

• B. Fields, C. Rhodes, "An Audience Steerable Automatic Music Director for Online Radio Broadcast," in International Conference on Music Information Retrieval, Kobe, Japan, Oct, 2009.

• R. Stewart, M. Magas, B. Fields, "decibel 151," in ACM SIGGRAPH 2009, New Orleans, Louisiana, USA, Aug 2009.

• EPSRC PhD Studentship, as part of the OMRAS2 project
• Goldsmiths University of London, Department of Computing Grant for Overseas Research
• Audio Engineering Society Educational Foundation Award
• University of Miami Frost School of Music departmental scholarship
• University of California, Santa Cruz, Jack Baskin School of Engineering, Honors in the Major, Computer Engineering