Welcome to UCSD's Computer Audition Laboratory. Listen up!


Supported by NSF CAREER grant IIS-1054960, "An integrated framework for multimodal music search and discovery".

---

faculty Gert Lanckriet (PI), Electrical & Computer Engineering Shlomo Dubnov, Music Lawrence Saul, Computer Science & Computer Engineering affiliated faculty Bhaskar Rao, Electrical & Computer Engineering graduate students Youngmin Cho, Computer Science & Engineering Emanuele Coviello, Electrical & Computer Engineering Katherine Ellis, Electrical & Computer Engineering Diane Hu, Computer Science & Engineering Janani Kalyanam, Electrical & Computer Engineering Daryl Lim, Electrical & Computer Engineering Brian McFee, Computer Science & Engineering alumni Luke Barrington, Electrical & Computer Enginnering Chih-Chieh Cheng, Computer Science & Engineering Riccardo Miotto, visiting student, University of Padua Arshia Cont, IRCAM David Torres, Anssur Corp Douglas Turnbull, Ithaca College

research projects Games for Crowdsourcing Data Collection Feature Kernel Combination Semantic Music Annotation and Retrieval CAL500 Data Set - 500 songs, 174 tags CATbox: Computer Audtion Toolbox for Matlab Music Segmentation and Boundary Detection Finding Musically Meaningful Words using Sparse CCA Musical Monitoring for Ambient Technology Temporal Models of Music Playlist modeling news October 2010: Emanuele Coviello (with coauthors) is awarded the ACM Multimedia 2010 Best Student Paper for "A New Approach To Cross-Modal Multimedia Retrieval". May 2010: Luke Barrington and Brian McFee are awarded the Qualcomm Innovation Fellowship for "Location-, Preference-, Demographic- and Content-Based Music Search and Recommendation". April 2010: Emanuele Coviello is awarded the 2010 Yahoo! Key Scientific Challenges Program for "Content-Based Music Video Tagging using Hierarchically Trained Dynamic Texture Mixtures". Apr 2010: CALab undergrads win Yahoo! Hack Day with their "Rock My World" local music discovery app! (open this link in your iPhone to try it out). Nov 2009: Luke, Reid and Gert's ISMIR paper about iTunes' Genius gets Slashdotted! October 2009: Emanuele Coviello is awarded the Premio Guglielmo Marconi Junior 2009 for his Master Thesis. July 2009: Herd It in the news! Wired, ZDNet, The Science Show (podcast available), UCSD and one for our Hebrew fans! Oct 2008: Dr. Arshia Cont completes his joint thesis from UCSD, CAL and IRCAM. Arshia's thesis Sep 2008: CAL system places first in MIREX auto-tagging contest abstract poster July 2008: Dr. Doug Turnbull becomes CAL's first Ph.D graduate. Doug's thesis

publications 2011 K. Ellis, E. Coviello, & G. Lanckriet - Semantic Annotation and Retrieval of Music Using a Bag of Systems Representation. ISMIR 2011 E. Coviello, R. Miotto, & G. Lanckriet - Combining Content-Based Auto-Taggers with Decision-Fusion. ISMIR 2011 B. McFee & G. Lanckriet - The natural language of playlists. ISMIR 2011 (data) B. McFee & G. Lanckriet - Large-scale music similarity search with spatial trees. ISMIR 2011 (code) Y. Vaizman & R.Y. Granot & J. Israel & G. Lanckriet - Modeling Dynamic Patterns for Emotional Content in Music. ISMIR 2011 S. Dubnov, G. Assayag and A. Cont - Audio Oracle analysis of Musical Information Rate, Proceedings of IEEE Semantic Computing Conference. . ICSC , September 2011 S. Dubnov, G. Assayag and A. Cont - On the Information Geometry of Audio Streams with Applications to Similarity Computing. IEEE Transactions on Audio, Speech and Language Processing, 19(4), pp. 837 - 846, 2011. J. Keshet, C-C Cheng, M. Stoehr, C. McAllester & L. K. Saul - Direct Error Rate Minimization of Hidden Markov Models. INTERSPEECH, August 2011 E. Coviello, A.B. Chan & G. Lanckriet - Time Series Models for Semantic Music Annotation. IEEE Transactions on Audio, Speech, and Language Processing, July 2011 C-C Cheng and B. Kingsbury - Arccosine Kernels: Acoustic Modeling with Infinite Neural Networks. ICASSP, May 2011 B. McFee, L. Barrington & G. Lanckriet - Learning content similarity for music recommendation. Submitted to IEEE Transactions on Audio, Speech and Language Processing, 2011. B. McFee & G. Lanckriet - Learning multi-modal similarity. Journal of Machine Learning Research (JMLR), February, 2011. 2010 B. McFee, L. Barrington & G. Lanckriet - Learning Similarity from Collaborative Filters. ISMIR 2010 R. Miotto, L. Barrington & G. Lanckriet - Improving Auto-tagging by Modeling Semantic Co-occurrences. ISMIR 2010 E. Coviello, L. Barrington, A.B. Chan & G. Lanckriet - Automatic Music Tagging With Time Series Models. ISMIR 2010 N. Koenigstein, G. Lanckriet, B. McFee and Y. Shavitt - Collaborative Filtering Based on P2P Networks. ISMIR 2010 B. McFee & G. Lanckriet - Metric learning to rank. ICML 2010 S. Dubnov - Musical Information Dynamics as Models of Auditory Anticipation. Machine Audition: Principles, Algorithms and Systems, ed. W. Weng, IGI Global publication, 2010. L. Barrington, A.B. Chan, G. Lanckriet - Modeling Music as a Dynamic Texture. IEEE Transactions on Audio, Speech and Language Processing 18-3 pp 602-612. (project page) C.-C. Cheng, F. Sha, & L. K. Saul - Online learning and acoustic feature adaptation in large margin hidden Markov models. EEE Journal of Selected Topics in Signal Processing 4(6): 926-942, 2010. 2009 C.-C. Cheng, F. Sha, and L. K. Saul - Large margin feature adaptation for automatic speech recognition. Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU-09). Merano, Italy. B. McFee and G. Lanckriet - Heterogeneous embedding for subjective artist similarity. Tenth International Symposium for Music Information Retrieval (ISMIR). Kobe, Japan. L. Barrington, R. Oda, G. Lanckriet - Smarter Than Genius? Human Evaluation of Muisc Recommender Systems. Tenth International Symposium for Music Information Retrieval (ISMIR). Kobe, Japan. D. J. Hu and L. K. Saul - A probabilistic model of unsupervised learning for musical-key profiles. Tenth International Society for Music Information Retrieval Conference (ISMIR-09). Kobe, Japan. S. Dubnov, Y. Kiyoki - Opera of Meaning: film and music performance with semantic associative search. Frontiers in Artificial Intelligence and Applications, Information Modelling and Knowledge Bases XX, Volume 190, pp. 384 – 391, 2009. C.-C. Cheng, F. Sha, and L. K. Saul - A fast online algorithm for large margin training of continuous-density hidden Markov models. In Proceedings of the Tenth Annual Conference of the International Speech Communication Association (Interspeech-09). Brighton, UK. L. Barrington, D. Turnbull, M. Yazdani, G. Lanckriet - Combining Audio Content and Social Context for Semantic Music Discovery. SIGIR, 2009. B. McFee, G. Lanckriet - Partial order embedding with multiple kernels. Twenty-sixth International Conference on Machine Learning (ICML), 2009. C.-C. Cheng, F. Sha, and L. K. Saul - Matrix updates for perceptron training of continuous-density hidden Markov models. In Proceedings of the Twenty Sixth International Conference on Machine Learning (ICML-09), pages 153-160. Montreal, Canada. Y. Cho and L. K. Saul - Learning dictionaries of stable autoregressive models for audio scene analysis. Twenty Sixth International Conference on Machine Learning (ICML), pages 169-176. Montreal, Canada. Y. Cho and L. K. Saul - Sparse decomposition of mixed audio signals by basis pursuit with autoregressive models. In Proceedings of the International Conference of Acoustics, Speech, and Signal Processing (ICASSP), pages 1705-1708. Taipei, Taiwan. L. Barrington, A.B. Chan, G. Lanckriet - Dynamic Texture Models of Music. In Proceedings of the International Conference of Acoustics, Speech, and Signal Processing (ICASSP). Taipei, Taiwan. S.Dubnov, M,J.Hinich - Analyzing several musical instrument tones using the randomly modulated periodicity model. Signal Processing, Volume 89 , Issue 1, pp 24-30, January 2009 2008 L. Barrington, M. Yazdani, D. Turnbull, G. Lanckriet - Combination of Feature Kernels for Semantic Music Retrieval. ISMIR 2008 D. Turnbull, L. Barrington, G. Lanckriet - Five Approaches to Coleecting Tags for Music. ISMIR 2008 C. C. Cheng, D. J. Hu, and L. K. Saul - Nonnegative matrix factorization for real time musical analysis and sight-reading evaluation. Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP-08), pages 2017-2020. Las Vegas, NV. D. Turnbull, L. Barrington, D. Torres, G. Lanckriet - Semantic Annotation and Retrieval of Music and Sound Effects. IEEE Transactions on Audio, Speech, and Language Processing, February 2008 bib S. Dubnov - Unified View of Prediction and Repetition Structure in Audio Signals. IEEE Transactions on Audio, Speech and Language Processing, Februrary 2008 S. Dubnov and G. Assayag - Memex and Composer Duets: computer aided composition using style modeling and mixing. Open Music Composers book 2, 2008 2007 Turnbull, Liu, Barrington & Lanckriet - A Game-Based Approach for Collecting Semantic Annotations of Music ISMIR, Vienna, Austria, September 2007. Torres, Turnbull, Barrington & Lanckriet - Identifying Words that are Musically Meaningful ISMIR, Vienna, Austria, September 2007. bib Turnbull, Lanckriet, Pampalk, & Goto - A Supervised Approach for Detecting Boundaries in Music Using Difference Features and Boosting ISMIR, Vienna, Austria, September 2007. Cont, Dubnov & Wessel - Realtime Multiple-pitch and Multiple-instrument Recognition For Music Signals using Sparse Non-negative Constraints. DAFx, Bordeaux, France, September 2007. Cont, Dubnov & Assayag - GUIDAGE: A Fast Audio Query Guided Assemblage. ICMC, Copenhagen, Denmark, August 2007. Dubnov, Cont & Assayag - Audio Oracle: A New Algorithm for Fast Learning of Audio Structures. ICMC, Copenhagen, Denmark, August 2007. Turnbull, Barrington, Torres & Lanckriet - Towards Musical Query-by-Semantic Description using the CAL500 Data Set. To appear in SIGIR, Amsterdam, July 2007 bib Cont, Dubnov & Assayag - Anticipatory Model of Musical Style Imitation using Collaborative and Competitive Reinforcement Learning. in Anticipatory Behavior in Adaptive Learning Systems: From Brains to Individual and Social Behavior Butz, M.V.; Sigaud, O.; Pezzulo, G.; Baldassarre, G. (Eds.), Pages 285-306, LNCS 4520, Springer Verlag. Barrington, Chan, Turnbull & Lanckriet - Audio Information Retrieval Using Semantic Similarity. International Conference on Acoustic, Speech and Signal Processing (ICASSP), Hawaii, April 2007 bib Sriperumbudur, Torres & Lanckriet - Sparse Eigen Methods by D.C. Programming. To appear in International Conference on Machine Learning (ICML), 2007 bib Turnbull, Barrington, Torres & Lanckriet - Exploring the Semantic Annotation and Retrieval of Sound. CAL Technical Report CAL-2007-01, San Diego, February 2007 2006 Turnbull, Barrington, Torres & Lanckriet - Modeling the Semantics of Sound NIPS Workshop on Advances in Models for Acoustic Processing, Vancouver, December 2006 Turnbull, Barrington & Lanckriet - Modeling Music and Words using a Multi-Class naive Bayes Approach. International Symposium on Music Information Retrieval (ISMIR), Victoria, October 2006 Cont - Realtime Multiple Pitch Observation using Sparse Non-negative Constraints. International Symposium on Music Information Retrieval (ISMIR), Victoria, October 2006. Cont, Dubnov & Assayag - A framework for Anticipatory Machine Improvisation and Style Imitation. Anticipatory Behavior in Adaptive Learning Systems (ABiALS), Rome, September 2006. Cont - Realtime Audio to Score Alignment for Polyphonic Music Instruments Using Sparse Non-negative constraints and Hierarchical HMMs. ICASSP'06, Toulouse, May 2006. Barrington, Lyons, Diegmann & Abe - Ambient Display Using Musical Effects. Intelligent User Interfaces (IUI), Sydney, January 2006