Musique algorithmique

Depuis le démarrage de la réflexion sur la composition assistée par ordinateur, première expérimentation musicale utilisant l’outil informatique, les systèmes de composition se sont tour à tour préoccupés d’infléchir ou de laisser l’initiative à la machine, et, parallèlement, de libérer totalement l’homme de certaines tâches de régulation, ou de lui laisser une part importante de création. Pour tenter de réduire la proportion de hasard, l'ordinateur fut utilisé pour ses fonctions de contrôle de l’automation. L’algorithme sert à résoudre des classes de problèmes grâce à une hiérarchisation des étapes dans une suite finie et ordonnée de règles. Cette forme opératoire de contrôle se retrouve à tous les niveaux de la programmation informatique. Pierre Barbaud débuta dans cet esprit fonctionnel ses travaux sur la composition “automatique” et mit au point avec Roger Blanchard en 1959 le programme ALGOM I-5 pour l’ordinateur Gamma 60 du Centre de calcul électronique de la compagnie Bull à

Algorithmic composition of melodies with deep recurrent neural networks

Florian François Colombo

A big challenge in algorithmic composition is to devise a model that is both easily trainable and able to reproduce the long-range temporal dependencies typical of music. Here we investigate how artificial neural networks can be trained on a large corpus of melodies and turned into automated mu- sic composers able to generate new melodies coherent with the style they have been trained on. We employ gated-recurrent unit (GRU) networks that have been shown to be particularly efficient in learning complex sequential activations with arbitrary long time lags. Our model processes rhythm and melody in parallel while modeling the relation between these two properties. Using such an approach, we were able to generate interesting complete melodies or suggest possible continuations of a melody fragment that is coherent with the characteristics of the fragment itself.

2016

Learning music composition with recurrent neural networks

Florian François Colombo

Throughout this thesis, we are interested in modeling music composition. To do so, we study the association of music theory concepts with the learning capabilities of recurrent neural networks. Especially, we explore numerical formalizations of music so that our models operate on data containing useful information to decide how to combine particular rhythms and notes in specified musical contexts. The first part introduces the Deep Artificial Composer, a generative model of monophonic melodies. We present a network architecture that considers the temporal and instantaneous relationships between the pitch and duration of notes. By combining Irish with klezmer melodies to train the Deep Artificial Composer, we study how it reacts to heterogeneous data. Furthermore, we show how to generate melodies containing Irish or Klezmer folk musicâs characteristics from our probabilistic model of notes. The second part presents BachProp, a model for the composition of polyphonic music. We discover how scores of different styles can be generated from models using neural networks. In particular, we train BachProp with Bachâs chorales and the English folk music corpus Nottingham. Also, we verify that generated compositions share specific properties with the original corpus it processes. Especially, our musical novelty statistics show that BachProp generates musical sequences as innovative as those present in the original corpora. Finally, a large audience appreciated the Ada string quartet performances of BachPropâs compositions. Whereas BachProp operates on any music in the usual MIDI format, the BeethovANN algorithm, introduced in the last part, needs the information contained in scores in the MusicXML format. These digital scores allow us to formalize relevant musical characteristics in order to generate music with BeethovANN. Thus, to create new voices that can be played in accompaniment to Beethoven string quartets, we take into account not only the note sequences, but also the harmonic progression, interactions between voices, and the rhythm of each instrument. Eventually, professional musicians misclassified BeethovANN musical phrases for Beethovenâs original compositions.

EPFL2021

Learning music composition with recurrent neural networks

Florian François Colombo

EPFL2021

Algorithmic composition of melodies with deep recurrent neural networks

Learning music composition with recurrent neural networks

Generating Musical Continuations with Repetition

Algorithmic composition of melodies with deep recurrent neural networks

Learning music composition with recurrent neural networks

Generating Musical Continuations with Repetition