Interests
  Papers
   - Journal
   - Conference
   - Other
  Talks
  Media
Now that I have graduated, I no longer maintain this research page. Check out my new Swarthmore webpage.

RESEARCH INTERESTS

My research focuses on Computer Audition, Machine Learning, and Music Information Retrieval.

Semantic Audio Annotation and Retrieval

We have created a computer audition algorithm that can both annotate novel audio tracks with semantically meaningful words and retrieve relevant tracks from a database of unlabeled audio content given a text-based query. We have used this algorithm to power the CAL Music Search Engine. See Project Page

Music Annotation Games

We can collect a large number of music tags by deploying casual, web-based video games. As players interact with the game, they provide semantic information about music that can be used to both directly index songs and train our computer audition system. You can help us collect data for this project by playing Listen Game.

Music Boundary Detection

A musical boundary is a transition between two musical segments such as a verse and a chorus. Our goal is to automatically detect musical boundaries using a supervised learning framework.

JOURNAL PAPERS

D. Turnbull, L. Barrington, D. Torres, G. Lanckriet
Semantic Annotation and Retrieval of Music and Sound Effects - bib
   IEEE Transactions on Audio, Speech, and Language Processing - to appear in February 2008

D. Turnbull, C. Elkan
Fast Recognition of Musical Genre using RBF Networks - slides - bib
   IEEE Transactions on Knowledge and Data Engineering - April 2005


CONFERENCE PAPERS

D. Turnbull, G. Lanckriet, E. Pampalk & M. Goto
A Supervised Approach for Detecting Boundaries in Music using Difference Features and Boosting - slides - bib
   International Symposium on Music Information Retrieval (ISMIR '07), Vienna, September 2007

D. Torres, D. Turnbull, L. Barrington & G. Lanckriet
Identifying Words that are Musically Meaningful - slides - bib
   International Symposium on Music Information Retrieval (ISMIR '07), Vienna, September 2007

D. Turnbull, R. Liu, L. Barrington & G. Lanckriet
A Game-Based Approach for Collecting Semantic Annotations of Music - slides - bib
   International Symposium on Music Information Retrieval (ISMIR '07), Vienna, September 2007

D. Turnbull, L. Barrington, D. Torres & G. Lanckriet
Towards Musical Query-by-Semantic Description using the CAL500 Data Set - slides - bib
  ACM Special Interest Group on Information Retrieval (SIGIR '07), Amsterdam, July 2007

L. Barrington, A. Chan, D.Turnbull & G.Lanckriet
Audio Information Retrieval Using Semantic Similarity - poster - bib
   International Conference on Acoustic, Speech and Signal Processing (ICASSP '07), Hawaii, April 2007

D. Turnbull, L. Barrington & G. Lanckriet
Modeling Music and Words using a Multi-Class naive Bayes Approach - slides - bib
  International Symposium on Music Information Retrieval (ISMIR '06), Victoria, October 2006


OTHER PAPERS

D. Torres, D. Turnbull, L. Barrington, B. K. Sriperumbudur & G. Lanckriet
Finding Musically Meaningful Words by Sparce CCA - bib
   NIPS Workshop on Music, Brain & Cognition, Vancouver, December 2007

L.Barrington, D.Turnbull, D. Torres & G.Lanckriet
Semantic Similarity for Music Retrieval - poster
  Music Information Retrieval Evaluation Exchange, Vienna, Sept 2007
  Audio Music Similarity Task - 3rd Place - No Statistical Significance between top 4 teams

D.Turnbull, L.Barrington, D.Torres & G.Lanckriet -
Modeling the Semantics of Sound
  NIPS Workshop on Advances in Models for Acoustic Processing, Vancouver, December 2006

D. Turnbull
Semantics from Sound: Modeling Audio and Text - slides
   Thesis Proposal, UC San Diego, May 2006

D. Turnbull, N. Alldrin
Failure Prediction in Hardware Systems - slides
   CSE221 Project - December 2003

D. Turnbull, N. Alldrin, A.Smith
Classifying Facial Expressions with RBF Networks
   CSE253 Final Project - March 2003


INVITED TALKS

Designing a Content-based Music Search Engine - abstract
   Seminar talk given at CMU, IRCAM (France), University of Bath (UK),
    University of London - Queen Mary (UK), UC San Diego, Princeton, Drexel, Columbia, and Microsoft Research
June 2007 through January 2008

Finding Music with Words
    Southern California Computing in Music Symposium (SCCiM '07)
   University of Southern California, February 17, 2007


IN THE MEDIA

News Article by Mark Freeman
Analytics is growing field in San Diego
   San Diego Union Tribune, Nov. 9, 2007

Online Article
Music Search Engine: Identifying Musically Meaningful Words
   Dr. Dobbs Portal, Sept 26, 2007

Interview by Lee Gomes
Computer Scientists Pull a Tom Sawyer to Finish Grunt Work
   The Wall Street Journal, June 27, 2007





Douglas Turnbull
dturnbul@cs.ucsd.edu
Created: November 2002
Last Updated: October 2007