CARLOS EDUARDO CANCINO-CHACÓN

Austrian Research Institute for Artificial Intelligence
Freyung 6/6
1010 Vienna, Austria

Email: carlos.cancino@ofai.at



RESEARCH INTERESTS

Computational Models of Expressive Music Performance
Computational Models of Music Cognition
Machine Learning (Deep Learning, Probabilistic Graphical Models)
Music Theory
Computational Creativity
Speech Processing



CURRICULUM VITAE

EDUCATION

2014 -
PhD. in Computer Science,
Johannes Kepler University of Linz, Austria.

Supervisor: Gerhard Widmer

2011 - 2014
M. Sc. in Electrical Engineering and Audio Engineering,
Graz University of Technology/University of Music and Performing Arts Graz, Austria.

Supervisor: Franz Pernkopf

2006 - 2011
Licenciatura como Físico (Bachelor's degree in Physics),
National Autonomous University of Mexico, Mexico City, Mexico.

Supervisor: Marcos Ley Koo.

1999 - 2011
Licenciatura en Concertista de Piano (Bachelor's degree in Piano Performance),
National Conservatory of Music, Mexico City, Mexico.

Supervisor: Héctor Alfonso Rojas Ramírez.

RESEARCH EXPERIENCE

2014 - present
Austrian Research Institute for Artificial Intelligence, Vienna, Austria
Intelligent Music Processing and Machine Learning Group

Researcher

2012 - 2014
Graz University of Technology, Graz, Austria
Signal Processing and Speech Communication Laboratory

Masters Student



TEACHING EXPERIENCE

2011
National Conservatory of Music, Mexico City, Mexico.
Course Lecturer (Level B)
Lecture Courses:
TPTC0101 Solfeo I
TPTC0306 Armonía Diatónica
TPTC0409 Armonía Cromática
PATC0101 Armonía Contemporánea



SCHOLARSHIPS

2012 - 2014
Scholarship 217746 of the Mexican National Council for Science and Technology (CONACyT)



PUBLICATIONS

PEER REVIEWED PUBLICATIONS

  • C. E. Cancino-Chacón, M. Grachten, K. Agres (2017).
    “From Bach to The Beatles: The Simulation of Human Tonal Expectation Using Ecologically-Trained Predictive Models”.
    In Proceedings of the 18th International Society for Music Information Retrieval Conference (ISMIR 2017). Suzhou, China. To appear. (supplementary materials)

  • C. E. Cancino-Chacón, T. Gadermaier, G. Widmer, M. Grachten (2017)
    “An Evaluation of Linear and Non-Linear Models of Expressive Dynamics in Classical Piano and Symphonic Music”.
    Machine Learning. Vol. 106(6). Springer. pp. 887-909. (pdf)

  • M. Grachten, C. E. Cancino-Chacón, T. Gadermaier, G. Widmer (2017)
    “Towards computer-assisted understanding of dynamics in symphonic music”.
    IEEE Multimedia. Vol. 24(1), pp. 36-46. (pdf)(author's accepted copy)

  • M. Grachten, C. E. Cancino Chacón (2017).
    “Temporal dependencies in the expressive timing of classical piano performances”.
    In the Routledge Companion of Embodied Music Interaction. M. Lessafre, M. Leman and P. J. Maes (Eds). Routledge. pp. 362-371. (pdf)(autor's accepted copy)

  • G. Velarde, T. Weyde, C. E. Cancino Chacón, D. Meredith, M. Grachten (2016).
    “Composer Recognition based on 2D-Filtered Piano-Rolls”.
    In Proceedings of the 17th International Society for Music Information Retrieval Conference (ISMIR 2016), New York City, NY, USA. (pdf)

  • T. Gadermaier, M. Grachten, C. E. Cancino Chacón (2016).
    “Modeling Loudness Variations in Ensemble Performance”.
    In Proceedings of the 2nd International Conference on New Music Concepts (ICNMC 2016). Treviso, Italy. (pdf)

  • C. E. Cancino Chacón and M. Grachten (2015).
    An evaluation of score descriptors combined with non-linear models of expressive dynamics in music”.
    In Proceedings of the 18th International Conference on Discovery Science (DS2015). Banff, Canada. (pdf)

  • S. Lattner, C. E. Cancino Chacón and M. Grachten (2015).
    Pseudo-Supervised Training Improves Unsupervised Melody Segmentation”.
    In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI). Buenos Aires, Argentina. (pdf)

  • S. Lattner, M. Grachten, K. Agres and C. E. Cancino Chacón (2015).
    Probabilistic Segmentation of Musical Sequences using Restricted Boltzmann Machines”.
    In Proceedings of the Fifth Biennial International Conference on Mathematics and Computation in Music (MCM2015). London, UK. (pdf)

  • K. Agres, C. E. Cancino Chacón, M. Grachten and S. Lattner (2015).
    Harmonics co-occurrences bootstrap pitch and tonality perception in music: Evidence from a statistical unsupervised learning model”.
    The Annual Meeting of the Cognitive Science Society (CogSci2015). Pasadena, CA, USA. (pdf)

  • C. E. Cancino Chacón, S. Lattner, M. Grachten (2014).
    “Developing tonal perception through unsupervised learning”.
    In Proceedings of the15th International Society for Music Information Retrieval Conference (ISMIR 2014). Taipei, Taiwan. (pdf)

  • C. E. Cancino Chacón and P. Mowlaee (2014).
    “Least Squares phase estimation of mixed signals”.
    In Proceedings of the 15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014). Singapore. (pdf)

  • M. Grachten, C. E. Cancino Chacón and G. Widmer (2014).
    Analysis and prediction of expressive dynamics using Bayesian linear models”.
    In Proceedings of the 1st International Workshop on computer and robotic Systems for Automatic Music Performance (SAMP14). Venice, Italy. (pdf)

  • S. Tschiatschek, C. E. Cancino Chacón, and F. Pernkopf (2013).
    Bounds for Bayesian Network Classifiers with Reduced Precision Parameters”,
    In Proceedings of the 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2013). Vancouver, Canada. (pdf)

EXTENDED ABSTRACTS

  • C. E. Cancino Chacón, M. Grachten (2016),
    “The Basis Mixer: A Computational Romantic Pianist”..
    Late Breaking/Demo at the 17th International Society for Music Information Retrieval Conference (ISMIR 2016), New York, USA. (pdf) (poster)

THESIS

  • C. E. Cancino Chacón (2014),
    “Tarkus Belief Propagation: On Message Passing Algorithms and Computational Commutative Algebra”.
    Graz University of Technology. Graz, Austria. (pdf)

  • C. E. Cancino Chacón (2011),
    Análisis teórico experimental de transductores de ultrasonido tipo Langevin”.
    National Autonomous University of Mexico. Mexico City, Mexico. (pdf)

TECHNICAL REPORTS

  • C. E. Cancino Chacón, M. Grachten (2016)
    Rendering Expressive Performances of Musical Pieces Through Sampling From Generative Probabilistic Models
    Technical Report, Austrian Research Institute for Artificial Intelligence, Vienna, TR-2016-01. (pdf)

  • M. Grachten, C. E. Cancino Chacón (2015).
    Strategies for Conceptual Change in Convolutional Neural Networks.
    Technical Report, Austrian Research Institute for Artificial Intelligence, Vienna, TR-2015-04. (pdf)

  • C. E. Cancino Chacón, M. Grachten, G. Widmer (2014),
    Bayesian Linear Models with Gaussian Priors for Musical Expression”,
    Technical Report, Austrian Research Institute for Artificial Intelligence, Vienna, TR-2014-12. (pdf)

  • C. E. Cancino Chacón (2013),
    “Reduced Precision Bayesian Network Classifiers”,
    Laboratory for Signal Processing and Speech Communication, Graz University of Technology. Graz, Austria. (pdf)


Music