The Continuator: Musical Interaction With Style
Reference: Journal of New Music Research,
Vol. 32, No. 3, pp. 333–341, 2003
Resources
Abstract
The Continuator is an interactive musical system designed to generate stylistically consistent
continuations of a musician’s playing in real time. It bridges the gap between traditional
interactive systems, which often lack stylistic coherence, and style imitation systems, which are
usually not interactive. The system learns statistical models of a performer’s style from
example material based on variable-order Markov chains, and uses them to generate responses
that follow the same stylistic patterns while remaining reactive and improvisatory. Experiments
with both professional musicians and children show that the Continuator can be perceived as a
meaningful musical partner, capable of extending the player’s ideas without merely copying them.
Highlights
- Introduces the Continuator, a real-time interactive system that imitates and extends a musician’s style.
- Uses variable-order Markov models to capture stylistic features such as rhythm, phrasing and harmony.
- Bridges two worlds: style imitation systems and interactive performance systems.
- Includes qualitative experiments with professional musicians and children, showing strong engagement and sense of “musical dialogue”.
- A foundational paper in machine improvisation and style modelling; widely cited in computer music and AI creativity research.
Keywords
Interactive music systems; machine improvisation; style modelling; variable-order Markov models;
musical interaction; AI music; human–computer interaction.
BibTeX
@article{pachet2003continuator,
title = {The Continuator: Musical Interaction With Style},
author = {Pachet, Fran{\c{c}}ois},
journal = {Journal of New Music Research},
volume = {32},
number = {3},
pages = {333--341},
year = {2003}
}Why this paper matters
This paper is one of the earliest and most influential demonstrations of machine
improvisation in a real performance context. The Continuator showed that a computer can learn
a performer’s style and respond in real time in a way that feels both coherent and surprising,
effectively acting as a “virtual musician”. It laid the conceptual and technical groundwork for
later systems in interactive AI music and remains a reference for research on stylistic
imitation and human–machine musical dialogue.