Search

Your search keyword '"Richard Groult"' showing total 32 results
Start Over Author "Richard Groult"
32 results on '"Richard Groult"'

1. I Keep Counting: An Experiment in Human/AI Co-creative Songwriting

Author

Gianluca Micchi, Louis Bigo, Mathieu Giraud, Richard Groult, and Florence Levé

Subjects
co-creativity, songwriting, artificial intelligence, structure, harmony, melody, lyrics, arrangement, Information technology, T58.5-58.64, Music, M1-5000
Abstract

Musical co-creativity aims at making humans and computers collaborate to compose music. As an MIR team in computational musicology, we experimented with co-creativity when writing our entry to the “AI Song Contest 2020”. Artificial intelligence was used to generate the song’s structure, harmony, lyrics, and hook melody independently and as a basis for human composition. It was a challenge from both the creative and the technical point of view: in a very short time-frame, the team had to adapt its own simple models, or experiment with existing ones, to a related yet still unfamiliar task, music generation through AI. The song we propose is called “I Keep Counting”. We openly detail the process of songwriting, arrangement, and production. This experience raised many questions on the relationship between creativity and machine, both in music analysis and generation, and on the role AI could play to assist a composer in their work. We experimented with 'AI as automation', mechanizing some parts of the composition, and especially 'AI as suggestion' to foster the composer’s creativity, thanks to surprising lyrics, uncommon successions of sections and unexpected chord progressions. Working with this material was thus a stimulus for human creativity.

Published
2021
Full Text
View/download PDF

2. Learning Sonata Form Structure on Mozart’s String Quartets

Author

Pierre Allegraud, Louis Bigo, Laurent Feisthauer, Mathieu Giraud, Richard Groult, Emmanuel Leguy, and Florence Levé

Subjects
computational music analysis, music structure, musical form, sonata form, Information technology, T58.5-58.64, Music, M1-5000
Abstract

The musical analysis of large-scale structures, such as the classical sonata form, requires to integrate multiple analyses of local musical events into a global coherent analysis. Modelling large-scale structures is still a challenging task for the research community. It includes building large and accurate annotated corpora, as well as developing practical and efficient tools in order to visualize the analyses of these corpora. It finally requires the conception of effective and properly evaluated MIR algorithms. We propose a machine learning approach for the sonata form structure on 32 movements from Mozart’s string quartets. We release an open dataset, encoding two reference analyses of these 32 movements, totaling more than 1800 curated annotations, as well as flexible visualizations of these analyses. We discuss the occurrence in this corpus of melodic, harmonic, and rhythmic features induced by pitches, durations, and rests. We investigate whether the presence or the absence of these features can be characteristic of the different sections forming a sonata form. We then compute the emission and transition probabilities of several Hidden Markov Models intended to match the structure of sonata forms at several resolutions. Our results confirm that the sonata form is better identified when the parameters are learned rather than manually set up. These results open perspectives on the computational analysis of musical forms by mixing human knowledge and machine learning from annotated scores.

Published
2019
Full Text
View/download PDF

24. Efficient pattern matching in degenerate strings with the Burrows–Wheeler transform

Author

Thierry Lecroq, Yannick Guesnet, Jacqueline W. Daykin, Arnaud Lefebvre, Martine Léonard, Laurent Mouchard, Bruce W. Watson, Élise Prieur-Gaston, Richard Groult, Modélisation, Information et Systèmes - UR UPJV 4290 (MIS), Université de Picardie Jules Verne (UPJV), Equipe Traitement de l'information en Biologie Santé (TIBS - LITIS), Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes (LITIS), Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Université de Rouen Normandie (UNIROUEN), Normandie Université (NU)-Université Le Havre Normandie (ULH), Normandie Université (NU)-Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), and Normandie Université (NU)

Subjects
Burrows–Wheeler transform, [INFO.INFO-DS]Computer Science [cs]/Data Structures and Algorithms [cs.DS], 0102 computer and information sciences, 02 engineering and technology, 01 natural sciences, Theoretical Computer Science, Combinatorics, 0202 electrical engineering, electronic engineering, information engineering, Pattern matching, Time complexity, Mathematics, Discrete mathematics, Sequence, String (computer science), Degenerate energy levels, String, Computer Science Applications, Algorithm, 010201 computation theory & mathematics, Signal Processing, 020201 artificial intelligence & image processing, Degenerate, Alphabet, Constant (mathematics), Information Systems
Abstract

A degenerate or indeterminate string on an alphabet Σ is a sequence of non-empty subsets of Σ. Given a degenerate string t of length n and its Burrows–Wheeler transform we present a new method for searching for a degenerate pattern of length m in t running in O ( m n ) time on a constant size alphabet Σ. Furthermore, it is a hybrid pattern matching technique that works on both regular and degenerate strings. A degenerate string is said to be conservative if its number of non-solid letters is upper-bounded by a fixed positive constant q; in this case we show that the search time complexity is O ( q m 2 ) for counting the number of occurrences and O ( q m 2 + occ ) for reporting the found occurrences where occ is the number of occurrences of the pattern in t. Experimental results show that our method performs well in practice.

Published
2019
Full Text
View/download PDF

25. Three Strategies for the Dead-Zone String Matching Algorithm

Author

Jacqueline Daykin, Richard Groult, Yannick Guesnet, Thierry Lecroq, Arnaud Lefebvre, Martine Léonard, Laurent Mouchard, Élise Prieur-Gaston, Bruce Watson, Modélisation, Information et Systèmes - UR UPJV 4290 (MIS), Université de Picardie Jules Verne (UPJV), Equipe Traitement de l'information en Biologie Santé (TIBS - LITIS), Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes (LITIS), Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Université de Rouen Normandie (UNIROUEN), Normandie Université (NU)-Université Le Havre Normandie (ULH), Normandie Université (NU)-Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), Normandie Université (NU), Jan Holub and Jan Ž\vdárek, and Lecroq, Thierry

Subjects
[INFO.INFO-DS]Computer Science [cs]/Data Structures and Algorithms [cs.DS], [INFO.INFO-DS] Computer Science [cs]/Data Structures and Algorithms [cs.DS], ComputingMilieux_MISCELLANEOUS
Abstract

International audience

Published
2017

26. Efficient pattern matching in degenerate strings with the Burrows-Wheeler transform

Author

Jacqueline Daykin, Richard Groult, Yannick Guesnet, Thierry Lecroq, Arnaud Lefebvre, Martine Léonard, Laurent Mouchard, Élise Prieur-Gaston, Bruce Watson, Modélisation, Information et Systèmes - UR UPJV 4290 (MIS), Université de Picardie Jules Verne (UPJV), Equipe Traitement de l'information en Biologie Santé (TIBS - LITIS), Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes (LITIS), Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Université de Rouen Normandie (UNIROUEN), Normandie Université (NU)-Université Le Havre Normandie (ULH), Normandie Université (NU)-Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), Normandie Université (NU), and Lecroq, Thierry

Subjects
FOS: Computer and information sciences, [INFO.INFO-DS]Computer Science [cs]/Data Structures and Algorithms [cs.DS], Computer Science - Data Structures and Algorithms, [INFO.INFO-DS] Computer Science [cs]/Data Structures and Algorithms [cs.DS], Data Structures and Algorithms (cs.DS), [INFO]Computer Science [cs], [INFO] Computer Science [cs]
Abstract

A degenerate or indeterminate string on an alphabet $\Sigma$ is a sequence of non-empty subsets of $\Sigma$. Given a degenerate string $t$ of length $n$, we present a new method based on the Burrows--Wheeler transform for searching for a degenerate pattern of length $m$ in $t$ running in $O(mn)$ time on a constant size alphabet $\Sigma$. Furthermore, it is a hybrid pattern-matching technique that works on both regular and degenerate strings. A degenerate string is said to be conservative if its number of non-solid letters is upper-bounded by a fixed positive constant $q$; in this case we show that the search complexity time is $O(qm^2)$. Experimental results show that our method performs well in practice., Comment: 7 pages, 1 figure

Published
2017

27. Les pierres musicales, un dispositif pédagogique interactif

Author

Julien Debove, David Durand, Marion Giraud, Mathieu Giraud, Richard Groult, Nicolas Guiomard-Kagan, Ophélie Hérouart, Emmanuel Leguy, Florence Levé, Nathan Marécaux, Hervé Midavaine, Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189 ( CRIStAL ), Ecole Centrale de Lille-Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut Mines-Télécom [Paris]-Université de Lille-Centre National de la Recherche Scientifique ( CNRS ), Algomus, Modélisation, Information & Systèmes ( MIS ), Université de Picardie Jules Verne ( UPJV ) -Université de Picardie Jules Verne ( UPJV ) -Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189 ( CRIStAL ), Ecole Centrale de Lille-Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut Mines-Télécom [Paris]-Université de Lille-Centre National de la Recherche Scientifique ( CNRS ) -Ecole Centrale de Lille-Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut Mines-Télécom [Paris]-Université de Lille-Centre National de la Recherche Scientifique ( CNRS ), Université de Picardie Jules Verne ( UPJV ), Algomus (Algorithmic Musicology), ANR-11-EQPX-0023/11-EQPX-0023,IRDIVE,Plateforme Recherche et Innovation dans les Environnements Visuels Numériques et Interactifs ( 2011 ), Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS), Modélisation, Information et Systèmes - UR UPJV 4290 (MIS), Université de Picardie Jules Verne (UPJV)-Université de Picardie Jules Verne (UPJV)-Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS), Université de Picardie Jules Verne (UPJV), and ANR-11-EQPX-0023,IRDIVE,Plateforme Recherche et Innovation dans les Environnements Visuels Numériques et Interactifs(2011)

Subjects
analyse musicale, [SHS.MUSIQ]Humanities and Social Sciences/Musicology and performing arts, [ SHS.MUSIQ ] Humanities and Social Sciences/Musicology and performing arts, [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD], pédagogie, interface tangible, musique, [ INFO.INFO-SD ] Computer Science [cs]/Sound [cs.SD], informatique musicale
Abstract

National audience; Les pierres musicales sont un dispositif interactif tangible pour expérimenter des notions musicales par le jeu et la manipulation d’objets, aussi bien pour le grand public que pour les musiciens apprenants. Constitué d’un support avec lequel les pierres interagissent, ce dispositif pédagogique se base sur notre faculté d’écoute et ne nécessite pas de connaissances préalables. Le participant résout des jeux en ordonnant les pierres, qui représentent chacune un son ou groupe de sons. Aidé par des messages sonores, il poursuit son travail d’auto-formation grâce à sa mémoire et sa capacité d’écoute. Les pierres font découvrir des éléments d’analyse musicale et sont utilisées lors d’événements de médiation scientifique. Le participant est ainsi un apprenant, se forgeant par l’expérimentation sensible des connaissances musicales (hauteurs et rythmes, similarités de mélodies). Ces connaissances peuvent s’approfondir, notamment en interaction avec un pédagogue.

Published
2017

28. Computational Analysis of Musical Form

Author

Florence Levé, Richard Groult, Mathieu Giraud, Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189 ( CRIStAL ), Ecole Centrale de Lille-Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut Mines-Télécom [Paris]-Université de Lille-Centre National de la Recherche Scientifique ( CNRS ), Algomus, Modélisation, Information & Systèmes ( MIS ), Université de Picardie Jules Verne ( UPJV ) -Université de Picardie Jules Verne ( UPJV ) -Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189 ( CRIStAL ), Ecole Centrale de Lille-Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut Mines-Télécom [Paris]-Université de Lille-Centre National de la Recherche Scientifique ( CNRS ) -Ecole Centrale de Lille-Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut Mines-Télécom [Paris]-Université de Lille-Centre National de la Recherche Scientifique ( CNRS ), Université de Picardie Jules Verne ( UPJV ), David Meredith, Algomus (Algorithmic Musicology), ANR-11-EQPX-0023,EQUIPEX IrDIVE, Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS), Modélisation, Information et Systèmes - UR UPJV 4290 (MIS), Université de Picardie Jules Verne (UPJV)-Université de Picardie Jules Verne (UPJV)-Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS), Université de Picardie Jules Verne (UPJV), and ANR-11-EQPX-0023,IRDIVE,Plateforme Recherche et Innovation dans les Environnements Visuels Numériques et Interactifs(2011)

Subjects
[ SHS.MUSIQ ] Humanities and Social Sciences/Musicology and performing arts, media_common.quotation_subject, music information retrieval, 02 engineering and technology, ACM : H.: Information Systems/H.5: INFORMATION INTERFACES AND PRESENTATION (e.g., HCI)/H.5.5: Sound and Music Computing, 050105 experimental psychology, Programming, 0202 electrical engineering, electronic engineering, information engineering, 0501 psychology and cognitive sciences, form analysis, media_common, Musical form, Cognitive science, Communication, ACM: H.: Information Systems/H.5: INFORMATION INTERFACES AND PRESENTATION (e.g., HCI)/H.5.5: Sound and Music Computing, music structure, [SHS.MUSIQ]Humanities and Social Sciences/Musicology and performing arts, Music psychology, business.industry, 4. Education, 05 social sciences, Art, Music theory, Music and emotion, New Interfaces for Musical Expression, [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD], 020201 artificial intelligence & image processing, Musical composition, Repetition (music), computational music analysis, business, [ INFO.INFO-SD ] Computer Science [cs]/Sound [cs.SD]
Abstract

International audience; Can a computer understand musical forms? Musical forms describe how a piece of music is structured. They explain how the sections work together through repetition, contrast, and variation: repetition brings unity, and variation brings interest. Learning how to hear, to analyse, to play, or even to write music in various forms is part of music education. In this chapter, we briefly review some theories of musical form, and discuss the challenges of computational analysis of musical form. We discuss two sets of problems, segmentation and form analysis. We present studies in music information retrieval (MIR) related to both problems. Thinking about codification and automatic analysis of musical forms will help the development of better MIR algorithms.

Published
2016
Full Text
View/download PDF

29. Computational Fugue Analysis

Author

Florence Levé, Emmanuel Leguy, Richard Groult, Mathieu Giraud, Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189 ( CRIStAL ), Institut National de Recherche en Informatique et en Automatique ( Inria ) -Ecole Centrale de Lille-Institut Mines-Télécom [Paris]-Université de Lille-Centre National de la Recherche Scientifique ( CNRS ), Algomus, Modélisation, Information & Systèmes ( MIS ), Université de Picardie Jules Verne ( UPJV ) -Université de Picardie Jules Verne ( UPJV ) -Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189 ( CRIStAL ), Institut National de Recherche en Informatique et en Automatique ( Inria ) -Ecole Centrale de Lille-Institut Mines-Télécom [Paris]-Université de Lille-Centre National de la Recherche Scientifique ( CNRS ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -Ecole Centrale de Lille-Institut Mines-Télécom [Paris]-Université de Lille-Centre National de la Recherche Scientifique ( CNRS ), Université de Picardie Jules Verne ( UPJV ), Algorithmic Musicology (Algomus), ANR-11-EQPX-0023,EQUIPEX IrDIVE, Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS), Modélisation, Information et Systèmes - UR UPJV 4290 (MIS), Université de Picardie Jules Verne (UPJV)-Université de Picardie Jules Verne (UPJV)-Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS), Université de Picardie Jules Verne (UPJV), and ANR-11-EQPX-0023,IRDIVE,Plateforme Recherche et Innovation dans les Environnements Visuels Numériques et Interactifs(2011)

Subjects
Ground truth, [SHS.MUSIQ]Humanities and Social Sciences/Musicology and performing arts, Computer science, repeating patterns, [ SHS.MUSIQ ] Humanities and Social Sciences/Musicology and performing arts, Speech recognition, [INFO.INFO-OH]Computer Science [cs]/Other [cs.OH], contrapuntal music, Harmonic (mathematics), Exposition (music), Scale (music), musical structure, Computer Science Applications, fugues, Music theory, Media Technology, [ INFO.INFO-OH ] Computer Science [cs]/Other [cs.OH], computational music analysis, Diatonic scale, Fugue, Music, Musical form
Abstract

One of the pinnacles of form in classical Western music, the fugue is often used in the teaching of music analysis and composition. Fugues alternate between instances of a subject and other patterns and modulatory sections, called episodes. Musicological analyses are generally built on these patterns and sections. We have developed several algorithms to perform an automated analysis of a fugue, starting from a score in which all the voices are separated. By focusing on the diatonic similarities between pitch intervals, we detect subjects and countersubjects, as well as partial harmonic sequences inside the episodes. We also implemented tools to detect subject scale degrees, cadences, and pedals, as well as a method for segmenting the fugue into exposition and episodic parts. Our algorithms were tested on a corpus of 36 fugues by J. S. Bach and Dmitri Shostakovich. We provide formalized ground-truth data on this corpus as well as a dynamic visualization of the ground truth and of our computed results. The complete system showed acceptable or good results for about one half of the fugues tested, enabling us to depict their design.

Published
2015
Full Text
View/download PDF

30. Subject and counter-subject detection for analysis of the Well-Tempered Clavier fugues

Author

Florence Levé, Richard Groult, Mathieu Giraud, Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS), Bioinformatics and Sequence Analysis (BONSAI), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria), Modélisation, Information et Systèmes - UR UPJV 4290 (MIS), and Université de Picardie Jules Verne (UPJV)

Subjects
Similarity (geometry), [SHS.MUSIQ]Humanities and Social Sciences/Musicology and performing arts, Matching (graph theory), Computer science, repeating patterns, Speech recognition, contrapuntal music, music information retrieval, symbolic music analysis, 02 engineering and technology, ACM H.5.5 (Sound and Music Computing), fugue analysis, 020204 information systems, Subject (grammar), [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD], 0202 electrical engineering, electronic engineering, information engineering, Music information retrieval, 020201 artificial intelligence & image processing, Diatonic scale, Fugue
Abstract

International audience; Fugue analysis is a challenging problem. We propose an algorithm that detects subjects and counter-subjects in a symbolic score where all the voices are separated, determining the precise ends and the occurrence positions of these patterns. The algorithm is based on a diatonic similarity between pitch intervals combined with a strict length matching for all notes, except for the first and the last one. On the 24 fugues of the first book of Bach's Well-Tempered Clavier, the algorithm predicts 66% of the subjects with a musically relevant end, and finally retrieves 85% of the subject occurrences, with almost no false positive.

Published
2012

31. Speeding up the detection of evolutive tandem repeats

Author

Laurent Mouchard, Richard Groult, Martine Léonard, Department of Computer Science (DCS), King‘s College London, Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes (LITIS), Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Université de Rouen Normandie (UNIROUEN), Normandie Université (NU)-Université Le Havre Normandie (ULH), Normandie Université (NU), Laboratoire de Recherche en Informatique d'Amiens (LaRIA), and Université de Picardie Jules Verne (UPJV)-Centre National de la Recherche Scientifique (CNRS)

Subjects
0303 health sciences, Sequence, Evolutive tandem repeats, General Computer Science, Series (mathematics), Computation, Hamming distance, DNA sequences, 0102 computer and information sciences, 01 natural sciences, [SDV.BIBS]Life Sciences [q-bio]/Quantitative Methods [q-bio.QM], Theoretical Computer Science, Combinatorics, 03 medical and health sciences, Tandem repeat, 010201 computation theory & mathematics, [INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM], Algorithm, ComputingMilieux_MISCELLANEOUS, 030304 developmental biology, Mathematics, Computer Science(all)
Abstract

We recently introduced evolutive tandem repeats with jump (using Hamming distance) (Proc. MFCS’02: the 27th Internat. Symp. Mathematical Foundations of Computer Science, Warszawa, Otwock, Poland, August 2002, Lecture Notes in Computer Science, Vol. 2420, Springer, Berlin, pp. 292–304) which consist in a series of almost contiguous copies having the following property: the Hamming distance between two consecutive copies is always smaller than a given parameter e. In this article, we present a significative improvement that speeds up the detection of evolutive tandem repeats. It is based on the progressive computation of distances between candidate copies participating to the evolutive tandem repeat. It leads to a new algorithm, still quadratic in the worst case, but much more efficient on average, authorizing larger sequences to be processed.

Published
2004

32. Traitement de la polyphonie pour l’analyse informatique de partitions musicales

Author

Guiomard-Kagan, Nicolas, Modélisation, Information et Systèmes - UR UPJV 4290 (MIS), Université de Picardie Jules Verne (UPJV), Algomus, Université de Picardie Jules Verne (UPJV)-Université de Picardie Jules Verne (UPJV)-Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS), Université de Picardie - Jules Verne, Mathieu Giraud, Florence Levé, Richard Groult, Algorithmic Musicology (Algomus), Modélisation, Information & Systèmes ( MIS ), Université de Picardie Jules Verne ( UPJV ), Université de Picardie Jules Verne ( UPJV ) -Université de Picardie Jules Verne ( UPJV ) -Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189 ( CRIStAL ), and Institut National de Recherche en Informatique et en Automatique ( Inria ) -Ecole Centrale de Lille-Institut Mines-Télécom [Paris]-Université de Lille-Centre National de la Recherche Scientifique ( CNRS ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -Ecole Centrale de Lille-Institut Mines-Télécom [Paris]-Université de Lille-Centre National de la Recherche Scientifique ( CNRS )

Subjects
Analyse musicale par ordinateur, [ INFO ] Computer Science [cs], Polyphony, [SHS.MUSIQ]Humanities and Social Sciences/Musicology and performing arts, [ SHS.MUSIQ ] Humanities and Social Sciences/Musicology and performing arts, Music information retrieval, Computer music, Recherche d'informations musicales, Informatique musicale, Polyphonie, [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD], [INFO]Computer Science [cs], [ INFO.INFO-SD ] Computer Science [cs]/Sound [cs.SD], Computational music analysis
Abstract

Music can be either monophonic (a single note sounds at each time) or polyphonic (several notes are sounding simultaneously, building harmonies). Understanding polyphonic music can be very complex. The goal of this thesis in computer music is to ease the analysis of polyphonic scores by splitting them in either monophonic voices or streams (coherent sets of notes).Research in this thesis first consists in comparing three voices separation algorithms and three streams separation algorithms. I propose an evaluation method to fairly compare these two approaches. This study shows the qualities of the Chew and Wu algorithm. The first step of this algorithm, which segments the score into “contigs” having a constant number of voices, is particularly robust.Further work of this thesis focuses on the second stage of the Chew and Wu algorithm that defines what contigs to connect and how to connect them. I improve these connections by using musical parameters such as the average pitch difference between neighbor contigs. The thesis concludes by evaluating simultaneously voice separation and pattern matching for the music analysis of fugues.; La musique peut être monophonique – une seule note est jouée à chaque instant – ou polyphonique – plusieurs notes sont jouées simultanément, formant des harmonies. Comprendre la musique polyphonique peut être très complexe. L’objectif de cette thèse en informatique musicale est de simplifier l’analyse de partitions polyphoniques en les décomposant en voix monophoniques ou en streams (ensembles cohérents de notes).Ces deux approches n’ayant jamais été confrontées, mes premiers travaux consistent à comparer trois algorithmes de séparation en voix et trois algorithmes de séparation en streams. Je propose pour cela des méthodes d’évaluation équitables pour ces deux approches. Les tests réalisés sur un corpus de musique classique et de musique pop ont mis en avant les qualités de l’algorithme de séparation en voix de Chew et Wu. La première étape de cet algorithme, qui segmente la partition en « contigs » avec un nombre de voix constant, est particulièrement robuste.La suite des travaux de cette thèse porte sur la seconde étape de l’algorithme de Chew et Wu, qui définit l’ordre de connexions des contigs et la manière de les connecter. J’améliore ces connexions en utilisant des paramètres musicaux comme la différence des moyennes des hauteurs des notes entre contigs voisins. La thèse se conclut en évaluant conjointement la séparation en voix et la recherche de motifs pour l’analyse musicale de fugues.

Published
2017

Catalog

Books, media, physical & digital resources
See catalog results