Musiikin laitos / Department of Music

____

OLIVIER LARTILLOT

____

Music Mining Plant

Computational tools are needed in order to efficiently manage and browse into the large amount of digital music databases largely available online. This project is aimed at conceiving an in-depth computational system for the analysis of musical databases, integrating all dimensions of musical representations -- low-level audio and symbolic descriptions, middle-level structures and configurations and high-level conceptualizations -- into a highly intercommunicating network.

• At low-level, we propose to unify the seemingly separate areas of study of audio transcription and symbolic segmentation into a common methodology of auditory scene analysis, and to guide these processes based on the expectation already inferred from the higher levels.

• At mid-level, detailed but nevertheless concise descriptions of the motivic content of music will be enabled within our proposed intensive pattern mining paradigm.

• At high-level, musical concepts are modelled as weighted combinations of features and structures, automatically selected among a very large area of possible choices, represented in a connectionist knowledge representation, such as artificial neural networks.

This will require a strong cooperation between disciplines as diverse as signal processing, cognitive science, artificial intelligence, knowledge discovery, information retrieval, operational research, computational engineering, semiotics and musicology. The resulting platform will offer further understanding of music perception and cognition, and can be applied both for advanced musicological studies and as a leading-edge platform for intelligent browsing of music databases.

____

*** PHD POSITION AVAILABLE. See here for more information. ***

____

Realisation

MIRToolbox:

• A Matlab toolbox dedicated to the extraction from audio files of musical features
• cf. "Products of Interest", Computer Music Journal, 32-4, pp. 94-105, 2008

____

Program Committees

Upcoming conferences:

• WEMIS 2009: Workshop on Exploring Musical Information Spaces
• ISMIR 2009: 10th International Society for Music Information Retrieval Conference

____

Teaching

SMC 2009, 6th Sound and Music Computing Conference:

• MIRtoolbox tutorial

ISSCCM 2009, International Summer School in Systematic, Comparative and Cognitive Musicology:

• MIRtoolbox workshop and Student Experiment

Music, Mind and Technology Master Program:

• Music Information Retrieval, MIRtoolbox and Matlab

____

Publications

Publications in international journals

Olivier Lartillot, Mondher Ayari, "Segmentation of Tunisian modal improvisation: Comparing listeners' responses with computational predictions", Journal of New Music Research, in press.

Olivier Lartillot, "Taxonomic categorisation of motivic patterns", Musicae Scientiae, Discussion Forum 4B, pp. 25-46, 2009.

Geoff Luck, Petri Toiviainen, Jaakko Erkkilä, Olivier Lartillot, Kari Riikkilä et al., "Modelling the relationships between emotional responses to, and musical content of, music therapy improvisations", Psychology of Music, 36-1, pp. 25-46, 2008.

Olivier Lartillot, Petri Toiviainen, "Motivic matching strategies for automated pattern extraction", Musicae Scientiae, Discussion Forum 4A, pp. 281-314, 2007.

Petri Toiviainen, Jaakko Erkkilä, Tuomas Eerola, Geoff Luck, Olivier Lartillot, "Music cognition research amidst the boreal forest", Cognitive Processing, 8-1, 2007.

Olivier Lartillot, Mondher Ayari, "Motivic pattern extraction in music, and application to the study of Tunisian Modal Music", South African Computer Journal, 36, pp. 16-28, June 2006.

Geoff Luck, Kari Riikkilä, Olivier Lartillot, Jaakko Erkkilä, Petri Toiviainen et al., "Exploring relationshops between level of mental retardation and features of music therapy improvisations: A computational approach", Nordic Journal of Music Therapy, 15-1, pp. 30-48, 2006.

Olivier Lartillot, "Multi-dimensional motivic pattern extraction founded on adaptive redundancy filtering", Journal of New Music Research, 34-4, pp. 375-393, Taylor & Francis, December 2005.

Olivier Lartillot, "A musical pattern discovery system founded on a modeling of listening strategies", Computer Music Journal, 28-3, pp. 53-67, MIT Press, Fall 2004.

Jakko Erkkilä, Olivier Lartillot, Geoff Luck, Kari Riikkilä, Petri Toiviainen, “Intelligent music systems in music therapy”, Music Therapy Today, 5-5, 2004.

Shlomo Dubnov, Gérard Assayag, Olivier Lartillot, Gill Bejerano, "Using machine-learning methods for musical style modeling", Computer, 36-10, pp. 73-80, IEEE Computer Society Press, October 2003.

Publications in peer-reviewed conferences

Tuomas Eerola, Olivier Lartillot, Petri Toiviainen, "Prediction of Multidimensional Emotional Ratings in Music From Audio Using Multivariate Regression Models", International Conference on Music Information Retrieval, Kobe, 2009.

Cyril Laurier, Olivier Lartillot, Tuomas Eerola, Petri Toiviainen, " Exploring relationships between audio features and emotion in music", Triennial Conference of European Society for the Cognitive Sciences of Music, Jyväskylä, 2009.

Olivier Lartillot, Tuomas Eerola, Petri Toiviainen, Jose Fornari, "Multi-feature modeling of pulse clarity: Design, validation, and optimization", International Conference on Music Information Retrieval, Philadelphia, 2008.

Olivier Lartillot, Tuomas Eerola, Petri Toiviainen, Jose Fornari, "Multi-feature modeling of pulse clarity: Design, validation, and optimisation", International Conference on Digital Audio Effects, Espoo, 2008.

Olivier Lartillot, Tuomas Eerola, Petri Toiviainen, Jose Fornari, "Multi-feature modeling of pulse clarity from audio", International Conference on Music Perception and Cognition, Sapporo, 2008.

Olivier Lartillot, Mondher Ayari, "Segmenting Arabic modal improvisation: Comparing listeners' responses with computer predictions", Conference on Interdisciplinary Musicology, Thessaloniki, 2008.

Olivier Lartillot, Petri Toiviainen, "MIR in Matlab (II): A Toolbox for Musical Feature Extraction From Audio", International Conference on Music Information Retrieval, Vienna, 2007.

Olivier Lartillot, Petri Toiviainen, "A Matlab Toolbox for Musical Feature Extraction From Audio", International Conference on Digital Audio Effects, Bordeaux, 2007.

Olivier Lartillot, Petri Toiviainen, Tuomas Eerola, "A Matlab Toolbox for Music Information Retrieval", Annual Conference of the German Classification Society, Freiburg, 2007. Selected for publication in C. Preisach, H. Burkhardt, L. Schmidt-Thieme, R. Decker, Data Analysis, Machine Learning and Applications, Studies in Classification, Data Analysis, and Knowledge Organization, Springer-Verlag, 2008.

Olivier Lartillot, Petri Toiviainen, "Melodic identification strategies for automated pattern extraction", International Conference on Music Perception and Cognition, Bologna, 2006.

Geoff Luck, Kari Riikkilä, Olivier Lartillot, Jaakko Erkkilä, Petri Toiviainen, "Diagnosing level of mental retardation from music therapy improvisations: A computational approach", International Conference on Music Perception and Cognition, Bologna, 2006.

Olivier Lartillot, "Pattern Mining in Discrete Time Series and Application to Music Mining", International Conference on Active Media Technology, Brisbane, 2006. Proceedings: Y. Li, M. Looi and N. Zhong, Advances in Intelligent IT: Active Media Technology 2006, series “Frontiers in Artificial Intelligence and Applications”, IOS Press, 2006.

Olivier Lartillot, "Efficient Extraction of Closed Motivic Patterns in Multi-Dimensional Symbolic Representations of Music", IEEE/WIC/ACM International Conference on Web Intelligence, Compiègne, IEEE Computer Society Press, 2005.

Olivier Lartillot, "Efficient Extraction of Closed Motivic Patterns in Multi-Dimensional Symbolic Representations of Music", International Conference on Music Information Retrieval, London, 2005.

Olivier Lartillot, "A Multi-Parametric and Redundancy-Filtering Approach to Pattern Identification", International Conference on Music Information Retrieval, Barcelona, 2004.

Olivier Lartillot, "An Adaptive Multi-Parametric and Redundancy-Filtering Approach for Motivic Pattern Discovery", Sound and Music Computing Conference, Paris, 2004.

Olivier Lartillot, "Discovering pertinent pattern through perceptual heuristics: Why and  how", International Conference on Music Information Retrieval, Baltimore, 2003.

Olivier Lartillot, "Perception-Based Musical Pattern Discovery", International Computer Music Conference, Singapour, 2003.

Olivier Lartillot, "Perception-Based Musical Pattern Discovery: Why and How", International Workshop on Content-Based Multimedia Indexing, Rennes, 2003.

Olivier Lartillot, "Modeling Musical Pattern Perception as an Incremental System of Inductive Inferences", Triennial Conference of the European Society for the Cognitive Sciences of Music, Hanovre, 2003.

Olivier Lartillot, "Integrating Pattern Matching into an Analogy-Oriented Pattern Discovery Framework", International Conference on Music Information Retrieval, Paris, 2002.

Olivier Lartillot, "Musical Analysis by Computer Following Cognitive Model of Induction of Analogies", International Computer Music Conference, Göteborg, 2002.

Olivier Lartillot, Shlomo Dubnov, Gérard Assayag, Gill Bejerano, "Automatic modeling of musical style", International Computer Music Conference, La Havana, 2001.

Francisco Iovino, Olivier Lartillot, Norbert Schnell, "Modalys in jMax : real-time modal synthesis", International Computer Music Conference, Beijing, 1999.

Book Chapters

Olivier Lartillot, "Motivic Pattern Extraction in Symbolic Domain", in Jialie Shen, John Shepard, Bin Cui, Ling Liu (ed.), Intelligent Music Information Systems: Tools and Methodologies, IGI Global, 2007.

Olivier Lartillot and Emmanuel Saint-James, "Automating Motivic Analysis Through the Application of Perceptual Rules", Music Query: Methods, Strategies, and User Studies (Computing in Musicology 13), MIT Press, 2005.

Olivier Lartillot and Gérard Assayag, "Modélisation et simulation du système complexe de perception de structures musicales", in Mondher Ayari (ed.), De la théorie à l'art de l'improvisation : Analyse de performances et modélisation musicale, Delatour, 2006.

Olivier Lartillot, "Analyse musicale, induction et analogie", in Gérard Assayag, Guerino Mazzola, François Nicolas (ed.) : Penser la musique avec les mathématiques?, Actes du Séminaire Mathématique/Musique/Philosophie, Delatour, 2006.

Olivier Lartillot, "Analyser sans réduire : un modèle cognitif d'induction d'analogies", in Jean-Marc Chouvel et Fabien Lévy (ed.), Observation, analyse, modèle : Peut-on parler d'art avec les outils de la science ? , Les Cahiers de l'Ircam, Ircam - L'Harmattan, 2002.

Communications in other conferences, symposia, etc.

Olivier Lartillot, "Motivic Pattern Mining", in E. Selfridge-Field, F. Wiering, G. A. Wiggins (Eds.), Knowledge representation for intelligent music processing, Dagstuhl Seminar Proceedings 09051, 2009.

Olivier Lartillot, Petri Toiviainen, Tuomas Eerola, "MIRtoolbox: an innovative environment, on top of Matlab, for music and audio analysis", Nordic MATLAB User Conference, Stockholm, 2008.

Olivier Lartillot, "Automated motivic analysis of Brahms' String Quartet based on multi-dimensional closed pattern mining", International Workshop on Computational Music Analysis, Paris, 2008.

Olivier Lartillot, "Automated extraction of motivic patterns and application to the analysis of Debussy's Syrinx", International Conference of the Society for Mathematics and Computation in Music, Berlin, 2007. Proceedings: T. Klouche, T. Noll, MCM 2007, CCIS 37, Springer-Verlag, 2009.

Geoff Luck, Jaakko Erkkilä, Petri Toiviainen, Olivier Lartillot, Kari Riikkilä, "A computational analysis of musical features: predicting type of mental disorder from music therapy clients' improvisations", International Conference of the Society for Mathematics and Computation in Music, Berlin, 2007. Proceedings: T. Klouche, T. Noll, MCM 2007, CCIS 37, Springer-Verlag, 2009.

Olivier Lartillot, Petri Toiviainen, Tuomas Eerola, "MIRtoolbox: työkalu musiikkiäänitteiden tietokoneavusteiseen analyysiin", National Symposium on Music Research, Oulu, 2007.

Olivier Lartillot, "Motivic Pattern Mining in Symbolic Music: Managing Multidimensionality and Transformations in Music", Annual Conference of the German Classification Society, Freiburg, 2007.

Olivier Lartillot, "An efficient algorithm for motivic pattern extraction based on a cognitive modeling", Open Workshop of Musicnetwork, Vienna, 2005.

Olivier Lartillot, "An efficient algorithm for motivic pattern extraction based on a cognitive modeling", Journées d’Informatiques Musicales, Saint-Denis, 2005.

Olivier Lartillot, "Automating Motivic Analysis Through a Modeling of Listening Strategies", National Symposium on Music Research, Jyväskylä, 2005.

Jaakko Erkkilä, Olivier Lartillot, Geoff Luck, Kari Riikkilä, Petri Toiviainen, “Älykkäät musiikkijärjestelmät musiikkiterapiassa”, National Symposium on Music Research, Jyväskylä, 2005.

Jaakko Erkkilä, Olivier Lartillot, Geoff Luck, Kari Riikkilä, Petri Toiviainen, “Intelligent Music Systems in Music Therapy”, European Music Therapy Congress, Jyväskylä, 2004.

Olivier Lartillot, "Perception-Based Advanced Description  of Abstract Musical Content", European Workshop on Image Analysis for Multimedia Interactive Services, London, 2003. Proceedings: E. Izquierdo, Digital Media Processing for Multimedia Interactive Services, World Scientific, 2003.

Olivier Lartillot, "Perception-Based Musical Pattern Discovery", Journées d’Informatiques Musicales, Montbéliard, 2003.

Olivier Lartillot, "Approche computationnelle de l'analyse musicale basée sur une modélisation informatique de la perception musicale", Colloque international : La notion de syntaxe en langue et en musique, Paris, 2003.

Olivier Lartillot, "Une analyse musicale suivant une heuristique perceptive", Atelier : "Fouille de données et recherche d'informations  dans des bases de données multimédia semi-structurées", Journées francophones d'Extraction et de Gestion des Connaissances, Lyon, 2003.

Olivier Lartillot, "Generalized Musical Pattern Discovery by Analogy from Local Viewpoints", International Conference on Discovery Science, Lübeck, 2002. Proceedings: S. Lange, K. Satoh, C. H. Smith, Discovery Science, LNCS 2534, Springer-Verlag, 2002.

Olivier Lartillot, "Comment analyser la musique dans toute sa complexité, à l'aide d'une modélisation informatique des mécanismes cognitifs d'induction et d'analogie", 17th International Musicological Society Congress, Leuven, 2002.

Olivier Lartillot, "Une appréciation de la créativité par induction du créé", ESCOM (European Society for the Cognitive sciences Of Music) 10th anniversary conference, Liège, 2002.

Gérard Assayag, Gill Bejerano, Shlomo Dubnov, Olivier Lartillot, "Automatic modeling of musical style", Journées d'Informatique Musicale, Bourges, 2001.

Reviews

Olivier Lartillot, Book review of "Analyse musicale : Sémiologie et cognition des formes temporelles" by Jean-Marc Chouvel, Musicae Scientiae, 12-2, pp. 339-349, 2008.

Olivier Lartillot, Petri Toiviainen, Tuomas Eerola, "Commentary on 'Comparative Analysis of Music Recordings from Western and Non-Western traditions by Automatic Tonal Feature Extraction' by Emilia Gómez, and Perfecto Herrera", Empirical Musicology Review, 3-3, pp. 157-160, 2008.