Last updated: Jul 2006

George Tzanetakis CV

Personal Information

• Tel : 250-721-8769
• Fax : 250-721-7292
• www : http://www.cs.uvic.ca/~gtzan/
• email: gtzan@cs.uvic.ca

Research Interests

Education

• Ph.D Computer Science, Princeton University 2002
  Thesis advisor: Perry Cook
• MA Computer Science, Princeton University 1999
• BSE Computer Science, Magna Cum Laude, University of Crete, Greece 1997

Music Education

• Music Theory and Composition - Music Department, Princeton University (10 courses while doing PhD in Computer Science) (1997-2001)
• Musicology, saxophone performance, and theory - Athenaum Conservatory, Athens, Greece (1993-1997)
• Piano and theory - Heraklion Conservatory, Greece (1985-1995)

Professional Employment History

• 2003-present Assistant Professor of Computer Science (cross-listed in Music, Electrical and Computer Engineering), University of Victoria, BC Canada 
• 2002-2003 Postdoctoral Fellow, Computer Science, Carnegie Mellon University (Computer Music Group, Informedia Group)
  Collaborators: Roger Dannenberg, Chris Atkenson, Alex Hauptmann, Howard Wactlar, Christos Faloutsos
• 1997-2002 Research Assistant, Princeton University
• Summer 2000 Chief designer of audio fingerprinting technology, Moodlogic Inc. San Francisco, CA
• Summer 1999 Summer Internship at the Computer Human Interaction Center (CHIC), SRI International, Menlo Park, CA
• 1995-1997 Computer Vision and Robotics Group, Inst. for Computer Science, FORTH, Heraklion, Greece
• 1995-1997 Private saxophone tutor, Heraklion, Greece
• 1993-1997 First alto saxophone, Heraklion Municipal Band
• 1994-1995 Information Systems and Software Technology Group, Inst. for Computer Science, FORTH, Heraklion, Greece
• Software Development Group, Computer Center, Univ. of Crete, Greece

Consultant Positions

• Moodlogic Inc. 2000-2002
• AllMusic Inc. Netherlands 2003-2005
• Memotrax Inc. 2004-present
  
• Teligence Communications Inc. 2005-present
  

Honors and Awards

• 2004 IEEE Signal Processing Society Young Author Paper Award for "Musical Genre Classification of Audio Signals", IEEE Transactions on Speech and Audio Processing, July 2002
  
• Ericsson Award of Excellence for senior thesis
  "The use of GSM speech compression for pitch modification in a greek text-to-speech system".
• Annual greek national foundation scholarships 1994-1996
• First prize 1996 Programming Contest, University of Crete, Greece

Professional Activities

• General co-chair Int. Conf. on Music Information Retrieval (ISMIR) 2006
  
• Technical Program co-chair Int. Computer Music Conference (ICMC) 2004
  
• Associate Editor Computer Music Journal 2003-present
• Associate Editor IEEE Transactions on Speech and Audio Processing 2005-present
• Guest Editor EURASIP Journal on Applied Signal Processing Special Issue on Music Informatio Retrieval (2005-2006)
• Program Committee Int. conf. on Music Information Retrieval (ISMIR) 2003
• Program Committee IEEE Int. conf. on Multimedia and Expo (ICME) 2006
  
• Porgram Committee ACM Multimedia 2006 (Workshop on Music and Computing)
  
• Program Committee RIAO 2007 Large Scale Semantic Access to Content
  
• Publications chair IEEE Workshop on Multimedia Signal Processing (MMSP) 2006
  
• NSERC (Natural Sciences and Engineering Research Council of Canada) external referee 2005
  
• NOW (Netherland Organization for Scientific Research, Dutch Research Council) referee 2005
  
• Reviewer 
  • Books:
    
  • John Wiley & Sons - Communications Technology Publishing, 2005
    
  • Journals:
    
  • Journal of Acoustical Society of America (JASA) 2004,2005
  • Informs Journal on Computing 2004
  • EURASIP Journal on Applied Signal Processing 2004
  • Computer Music Journal 2003, 2004, 2005
    
  • IEEE Trans. on Speech and Audio Processing 2002-2006
  • IEEE Trans. on Information Systems 2003
  • IEEE Trans. on Signal Processing 2003, 2006
    
  • Speech Communications 2002,2005
  • Journal of New Music Research 2002, 2005
    
  • IEEE Trans. on Multimedia 2002,2004-2006
  • Machine Learning Journal 2005
    
  • ACM Transactions on Multimedia Computing, Communications and Applications 2006
    
  • Journal of the American Society for Information Science and Technology 2006
    
  • ACM Multimedia Systems Journal (Springer) 2006
    
  • Communications of the ACM, 2006
    
  • Conferences:
    
  • Int. Symposium on Algorithms and Computation 2004
  • IEEE Worshop on Applications of Signal Processing
          to Audio and Acoustics (WASPAA), 1999, 2001, 2003
  • Int. Conf. on Auditory Display (ICAD) 2000
  • Int. Conf. on Music Information Retrieval (ISMIR) 2002-2005
    
  • Int. FLAIRS Conference - AI in Music and Art 2005
  • Int. Computer Music Conference (ICMC) 2004, 2005
  • Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP) 2005
    
  • Pervasive Computing 2006
  • Visual Computing and Multimedia 2006
    
  • ACM SIGGRAPH 2006
    
• Memberships
• Association for Computing Machinery (ACM)
• Institute of Electrical and Electronics Engineers (IEEE) Computer and Signal Processing Society
• International Computer Music Association (ICMA)
• International Community for Auditory Display (ICAD)

Contributions to Books

1. Where is the music in music information retrieval
   Tzanetakis, G MMIR MultiMedia Information Retrieval: Metodologie ed Esperienze Internazionali di Content-based Retrieval per L' informazione e la Documentazione, R. Raieli, et P. Innocenti (Eds), AIDA, Roma, 2004, ISBN 88-901144-9-5, 2004
2. Audio Information Retrieval using MARSYAS
   Tzanetakis, G., and P. Cook (to appear) Current Research in Music Information Retrieval: Searching Audio, Midi and Notation, D. Byrd and J.S. Downie (Eds), Kluwer Academic Publishers 2004

Refereed Journal Publications

1. An experimental comparison of audio tempo induction algorithms
   Gouyon, F. et al. IEEE Transactions on Speech and Audio Processing (to appear Sep. 2006)
   
2. A comparative evaluation of search techniques for Query-by-Humming using the Musart  Testbed
   Dannenberg R. et a. Journal of American Society for Information Science 58(3) (February 2007) (to appear)
   
3. Visualization in Audio-Based Music Information Retrieval
   
Cooper, M., Foote, J., Pampalk, E., Tzanetakis, G. Computer Music Journal 30(2)

4. A scalable peer-to-peer system for music content and information retrieval
   Tzanetakis, G., J.Gao, and P.Steenkiste  Computer Music Journal 28(2) (Special Issue on Music Information Retrieval) 2004
5. The MUSART testbed for query-by-humming evaluation
   Dannenberg, R. et al. Computer Music Journal 28(2) (Special Issue on Music Information Retrieval) 2004
6. Pitch Histograms in Audio and Symbolic Music Information Retrieval
   Tzanetakis, G. Ermolinskyi, A. and Cook,P., Journal of new Music Research, 32(2),  2003
7. Musical Genre Classification of Audio Signals
   Tzanetakis, G. and Cook,P., IEEE Transactions on Speech and Audio Processing, 10(5), July 2002
8. Music Analysis and Retrieval Systems
   Tzanetakis, G. and Cook, P., Journal of American Society for Information Science and Technology, 55(12), Special Issue on Sound and Music Information Retrieval  2004
9. MARSYAS: A Framework for Audio Analysis
   Tzanetakis, G. and Cook, P., Organized Sound 4(3), Cambridge University Press, 2000
10. Early Experiences and Challenges in Building and using a Scalable Display Wall System
    Li, K. et al., IEEE Computer Graphics and Applications, "Off the Desktop: Large-Format Displays", 20(4), 2000

Refereed Conference Publications

1. Learning Indirect Acquistion of Instrumental Gestures using Direct Sensors
   G. Tzanetakis, A. Kapur and A. Tindale, Proc. IEEE Workshop on Multimedia Signal Processing (MMSP), 2006
   
2. Flexible Scheduling for DataFlow Audio Processing
   N. Burroughs, A. Parkin and G. Tzanetakis, Proc. Int. Computer Music Conf. (ICMC), 2006
   
3. Interactive Content-Aware Music Browsing using the Radio Drum
   J. Murdoch, G. Tzanetakis Li, Proc. IEEE Int. Conf. on Multimedia and Expo (ICME), 2006
4. Spatial Sound Rendering using Measured Room Impulse Responses   
    Li, Y., S. Bellamy, P.Driessen, and  G.Tzanetakis Proc. IEEE Int. Symposium on Signal Processing and Information Technology, 2006
   
5. LogoRhythms: Introductory Audio Programming for Computer Musicians in a Functional Language Paradigm
   Hechmer, A., Tindale, A., and G.Tzanetakis Proc. IEEE Frontiers in Educaction, 2006
   
6. Subband-based Drum Transcription for Audio Signals
   Tzanetakis, G., A. Kapur, R. McWalter Proc. IEEE Workshop on Multimedia Signal
   Processing (MMSP) 2005
   
7. Audio-based Gender Identification using Bootstrapping
   Tzanetakis, G.  Proc. IEEE PacRim Conference 2005
   
8. A Comparison of Sensor Strategies for Capturing Percussive Gestures
   Tindale, A., A. Kapur, G. Tzanetakis, P. Driessen.  Proc. Int. Conf. on New Interfaces for Musical Expression (NIME), 2005
9. Implicit Patching for Dataflow-based Audio Analysis and Synthesis
   Bray, S., and G.Tzanetakis. Proc. Int. Computer Music Conf. (ICMC) 2005
10.  New music interfaces for rhythm-based retrieval
    Kapur, A., R. McWalter and G. Tzanetakis. Proc. Int. Conf. on Music Information Retrieval (ISMIR), 2005
11.  Distributed audio feature extraction for music
    Bray, S. and G. Tzanetakis. Proc. Int. Conf. on Music Information Retrieval (ISMIR), 2005
    
12.  Gesture-Based Affective Computing on Motion Capture Data
    Kapur, A., A. Kapur, N. Virji-Babul, G. Tzanetakis, P. Driessen. Proc. Int. Conf. on Affective Computing and Intelligent Interaction (ACII), 2005
    
13. A framework for sonification of motion capture data
    Kapur, A., G.Tzanetakis, N. Virji-Babul, G. Wang, and P. Cook,b Proc. Int. Conf. on Digital Audio Effects (DAFX), 2005
14. Indirect acquisition of percussion gestures using timbre recognition
    Tindale, A., A.Kapur, W.A. Schloss, and G.Tzanetakis. Proc. Int. Conf. on Interdisciplinary Musicology (CIM), 2005 
15. Query-by-Beat-Boxing: Music Retrieval for the DJ
    Kapur, A., M.Benning and G. Tzanetakis. Proc. Int. Conf. on Music Information Retrieval (ISMIR), Barcelona, Spain, 2004
16. Retrieval of percussion gestures using timbre classification
    Tindale, A., A.Kapur, G. Tzanetakis and I.Fujinaga. Proc. Int. Conf. on Music Information Retrieval (ISMIR), Barcelona, Spain, 2004
17. Audio-Based Gesture Extraction on the ESITAR Controller
    Kapur, A, G.Tzanetakis and P.Driessen. Proc. Int. Conf. on Digital Audio Effects (DAFX), Naples, Italy, 2004
18. Song-specific bootstrapping of singing voice structure
    Tzanetakis. G. Proc. IEEE Int. Conf. on Multimedia and Expo (ICME), Taipei, Taiwan 2004
19.  A comparison of human and automatic musical genre classification
    Lippens, S. et al. Proc. IEEE Int. Conf. on Audio, Speech and Signal Processing (ICASSP), Montreal, Canada, 2004
20.  Building audio classifiers for broadcast news retrieval
    Tzanetakis, G., M.Y.Chen Proc. IEEE Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS), Lisbon, Portugal, 2004.
21.  A scalable Peer-to-Peer System for Music Content and Information Retrieval
    Tzanetakis, G., Gao, J., Steenkiste, Proc. Int. Conf. on Music Information Retrievla (ISMIR), 2003
22. Informedia at TRECVID 2003: Analyzing and Searching Broadcast News Video
     A. Hauptman et al. Proc. TRECVID 2003
23.  The Musart Testbed for Query-by-humming evaluation 
    Birmingham, W., Dannenberg, Hu, N., R., Meek, C., Pardo, B., Tzanetakis, G., Proc. Int. Conf
    on Music Information Retrieval (ISMIR), 2003
    
24. Factors in Automatic Musical Genre Classification of Audio Signals
    Li, T, Tzanetakis, G. Proc. IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2003
25. Polyphonic Audio Matching and Alignment for Music Retrieval
    Hu, N., Dannenberg, R., Tzanetakis, G. Proc. IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2003
26. Musescape: an Interactive Content-aware Music Browser
    Tzanetakis, G., Proc. Int. Conf. on Digital Audio Effects (DAFX), 2003
27. Musescape: a Tool for Changing Music Collections into Libraries
    Tzanetakis, G., Proc. European Conference on Digital Libraries (ECDL), 2003
28. Content-based Retrieval of Music in Scalable Peer-to-Peer Networks
    Gao, J., Tzanetakis, G., Steenkiste, P. Proc. IEEE Conf. on Multimedia and Expo (ICME) 2003
29. Toward an Intelligent Editor for Jazz Music
    Tzanetakis, G., Hu,N. and Dannenberg, R. Proc. IEEE Workshop on Image Analysis for Multimedia Interactive Systems (WIAMIS), 2003
30. Beyond the Query-by-Examle paradigm: New Query Interfaces for Music Information Retrieval
    Tzanetakis, G., Ermolinskyi, A., Cook, P., Proc. Int. Computer Music Conference (ICMC), 2002
31. Human Perception and Computer Extraction of Beat Strength
    Tzanetakis, G., Essl, G. and Cook, P., Proc. Int. Conf. on Digital Audio Effects (DAFX) 2002
32. Pitch Histograms in Audio and Symbolic Music Information Retrieval
    Tzanetakis, G., Ermolinskyi, A., Cook, P., Proc. Int. Conf. on Music Information Retrieval (ISMIR), 2002
33. Enhancing Sonic Browsing using Audio Information Retrieval
    Brazil, E., Tzanetakis, G., Cook, P. and Fernstrom, M., Proc. Int. Conf. on Auditory Display (ICAD), 2002
34. Automatic Musical Genre Classification of Audio Signals
    Tzanetakis, G., Essl, G. and Cook, P., Proc. Int. Symposium on Music Information Retrieval (ISMIR), 2001
35. Panel: New Directions in Music Information Retrieval
    Dannenberg, R., Foote, J., Weare, C. and Tzanetakis, G. Int. Computer Music Conference (ICMC), 2001
36. Audio Analysis using the Discrete Wavelete Transform
    Tzanetakis, G., Essl, G. and Cook, P., Proc. WSES Int. Conf. on Acoustics and Music: Theory and Applications (AMTA), 2001
    Reprinted in "Mathematics and Simulation with Biological, Economical and Musicoacoustical Applications", WSES Press, 2001
37. MARSYAS3D: A Prototype Audio Browser-Editor using a Large Scale Immersive Visual and Audio Display
    Tzanetakis, G., and Cook, P., Proc. Int. Conf. Auditory Display (ICAD), 2001
38. 3D Graphics Tools for Isolated Sound Collections
    Tzanetakis, G. and Cook,P., Proc. Int. Conf. on Digital Audio Effects (DAFX), 2000
39. Audio Information Retrieval (AIR) Tools
    Tzanetakis,G. and Cook, P., Proc. Int. Symposium on Music Information Retrieval (ISMIR), 2000
40. Sound Analysis using MPEG compressed Audio
    Tzanetakis,G. and Cook, P., Proc. IEEE Int. Conf. Acoustics, Speech and Signal Proc. (ICASSP), 2000
41. Experiments in Computer-assisted Annotation of Audio
    Tzanetakis,G. and Cook, P., Proc. Int. Conf. Auditory Display (ICAD), 2000
42. Multimedia Structuring using Trees
    Tzanetakis,G. and Julia, L., Proc. RIAO Content-based Multimedia Information Access, 2000
43. Multi-feature Segmenation for Audio Browsing and Annotation
    Tzanetakis, G. and Cook, P., Proc. IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 1999
44. A Framework for Audio Analysis based on Classification and Temporal Segmentation
    Tzanetakis,G. and Cook, P., Proc. Workshop on Music Technology and Audio Euromicro, 1999
45. N >> 2 Multi-speaker Display Systems for Virtual Reality and Spatial Audio Projection
    Cook, P. Essl, G., Tzanetakis, G. and Trueman, D., Proc. Int. Conf. Auditory Display (ICAD), 1998
46. Motion estimation based on affine moment invariants
    Tzanetakis, G., Traka, M. and Tziritas, G., Proc. Int. Conf. Auditory Display (ICAD), 1998

Other publications

• PHD thesis: "Manipulation, Analysis and Retrieval Systems"
  availabe as TR-651-02, Computer Science Department, Princeton University
• Senior thesis: "The use of GSM speech compression for pitch modification in a greek text-to-speech system"

Tutorials at International Conferences

• Music Information Retrieval, Int. Conf. on Multimedia and Expo (ICME), 2006
  
• Music Information Retrieval, Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2005
  
• Software Frameworks for Analysis for Audio and Music Signals (with Xavier Amatriain) Int. Conf. on Music Information Retrieval (ISMIR), 2004
  
• Music Information Retrieval
  Int. Computer Music Conference (ICMC), 2004
  
• Audio Feature Extraction
  IEEE Int. Conf. on Mulimedia and Expo (ICME)
  
• Music Information Retrieval for Audio Signals
  Int. Conference on Music Information Retrieval (ISMIR), 2002, 2003
• Music Information Retrieval using Audio Representations
  European Conference on Digital Libraries (ECDL), Trodheim, Norway 2003

Invited presentations

• A personal history of Music Information Retrieval, BIRS Workshop on Multimedia and Mathematics, Banff, Canada, 2005
  
• Music and Human Computer Interaction, Vancouver Studies in Cognitive Science, 2005
  
• The future of music software, University of Pompeu Fabra, Barcelona, Spain, 2005
  
• Music Retrieval, University of Porto, Portugal, April, 2004
  
• Music-Specific Audio Analysis Microsoft Research, July 2004
• Beyond Retrieval, Reflections on Musical Content
  Workhop: Multimedia Information Retrieval in Business Applications, Franhofer Institute, Germany 2003
• Music Analysis and Retrieval for Audio Signals
  Spoken Spoken Language Systems Group, MIT Laboratory for Computer Science, 2002
• Manipulation, Analysis and Retrieval Systems for Audio Signals
  Music Technology Group, Music Department McGill University, 2002
• An Overview of Audio Information Retrieval
  Hearing Seminar, Computer Center for Research in Music and Acoustics (CCRMA) Stanford 2001

Software

• Marsyas - framework for computer audition research
  http://marsyas.sourceforge.net

  The software provides a variety of common building blocks for audio analysis and a dataflow-based development environment that facilitates experimentation and creation of real time audio analysis algorithms and tools. Projects created using Marsyas by other parties include: game-terrain generation based on music analysis, music-driven computer animation, instrument classification, audio fingerprinting and real-time music-speech detection. The software is provided as free software under the GNU public licence (GPL) and compiles under Linux, Solaris, Irix, Windows (Visual Studio + Cygwin) and MacOS X.

• Moodlogic Audio Fingerprinting
  http://www.moodlogic.com

  Content-based audio fingerpriting technology used for metadata annotation with approximately 100.000 users. Characteristics include: extraction 2 secs, matching speed (20 milliseconds) (in 1.5 million songs), fingerprint size = 300 bytes, accuracy = 100% (13500 queries in 1.5 million songs)

Available upon request