The Continuator: Musical Interaction With Style
By François Pachet. International Conference on Mathematics and Computing, 2003
459 citations recorded by the source corpus.
We propose a system, the Continuator, that bridges the gap between two classes of traditionally incompatible musical systems: (1) interactive musical systems, limited in their ability to generate stylistically consistent material, and (2) music imitation systems, which are fundamentally not interactive. Our purpose is to allow musicians to extend their technical ability with stylistically consistent, automatically learnt material. This goal requires the ability for the system to build operational representations of musical styles in a real time context. Our approach is based on a Markov model of musical styles augmented to account for musical issues such as management of rhythm, beat, harmony, and imprecision. The resulting system is able to learn and generate music in any style, either in standalone mode, as continuations of musician’s input, or as interactive improvisation back up. Lastly, the very design of the system makes possible new modes of musical collaborative playing. We describe the architecture, implementation issues and experimentations conducted with the system in several real world contexts.
Subfields: Architecture, Computer Vision and Pattern Recognition, Signal Processing
View Paper: https://www.semanticscholar.org/paper/ce03eab90a7ce28f3f51db004d2521498c89b240
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Architecture
In Computer Vision and Pattern Recognition
- Eitan Wilf
- Jean-Julien Aucouturier
- François Pachet
- Hendrik Purwins
- Ricard Marxer
- Simon Colton
- Geraint A. Wiggins
- Lawrence Carin
In Signal Processing
- Eitan Wilf
- Jean-Julien Aucouturier
- François Pachet
- Hendrik Purwins
- Ricard Marxer
- Simon Colton
- Geraint A. Wiggins
- David B. Dunson
Citations in the corpus
- Computational Creativity: The Final Frontier? (2012, background): “…have been sold [24]; theorems from the HR discovery system have appeared in the mathematical literature [11, 55]; the Ludi system [5] has invented a popular board game, for which people have paid money; and the Continuator jazz impro-visation system has played alongside professional musicians [46].”
- Representing Musical Genre: A State of the Art (2003, background): “This is surprising, especially because time-modeling (notably HMMs) has proved to be a successful framework for the related problem of “style recognition,” mentioned above (see notably recent work by Pachet, 2002).”
- Designing Creative AI Partners with COFI: A Framework for Modeling Interaction in Human-AI Co-Creative Systems (2022, unknown): “1996 Improv [125] 1999 GeNotator [149] 2000 NEvAr [103] 2001 Metasynth [38] 2003 Facade [109], continuator [122] 2005 LOGTELL [30] 2008 CombinFormation[83], REQUEST [131], miCollage[159], BeatBender [91], WEVVA [116] 2009 Terrain Sketching [57], JNETIC [14], Synthetic Audience [120], The Poetry Mach”
- Toward an Anthropology of Computer-Mediated, Algorithmic Forms of Sociality (2013, methodology): “Thus, at one point during our conversation, James mentioned The Continuator , a software written by the music technology scientist, Francois Pachet (Pachet 2003; Wilf 2013 a ).”
- Unsupervised Incremental Online Learning and Prediction of Musical Audio Signals (2015, background): “For music transcription [4], prediction [5], [6], representation [7], [8], automatic accompaniment, or human-machineimprovisation [9], [10], a traditional system usually is based either on symbolic data instead of audio input, or on classifiers that are pre-trained on a labelled data base [4].”