Assisted Lead Sheet Composition Using FlowComposer

We present FlowComposer, a web application that helps users compose musical lead sheets, i.e. melodies with chord labels. FlowComposer integrates a constraint-based lead sheet generation tool in which the user retains full control over the generation process. Users specify the style of the lead sheet by selecting a corpus of existing lead sheets. The system then produces a complete lead sheet in that style, either from scratch, or from a partial lead sheet entered by the user. The generation algorithm is based on a graphical model that combines two Markov chains enriched by Regular constraints, representing the melody and its related chord sequence. The model is sampled using our recent result in efficient sampling of the Regular constraint. The paper reports on the design and deployment of FlowComposer as a web-service, part of an ecosystem of online tools for the creation of lead sheets. FlowComposer is currently used in professional musical productions, from which we collect and show a number of representative examples.

[1]  Frederick P. Brooks,et al.  An experiment in musical composition , 1957, IRE Trans. Electron. Comput..

[2]  Bob L. Sturm,et al.  The "Beyond the Fence" Musical and "Computer Says Show" Documentary , 2016, ICCC.

[3]  Ran El-Yaniv,et al.  On Prediction Using Variable Order Markov Models , 2004, J. Artif. Intell. Res..

[4]  Jürgen Schmidhuber,et al.  Learning the Long-Term Structure of the Blues , 2002, ICANN.

[5]  François Pachet,et al.  Exact Sampling for Regular and Markov Constraints with Belief Propagation , 2015, CP.

[6]  François Pachet,et al.  A Comprehensive Online Database of Machine-Readable Lead-Sheets for Jazz Standards , 2013, ISMIR.

[7]  text,et al.  Flow­machines: Cp Techniques to Model Style in Music and Text | Association for Constraint Programming Association for Constraint Programming , .

[8]  Gilles Pesant,et al.  A Regular Language Membership Constraint for Finite Sequences of Variables , 2004, CP.

[9]  François Pachet,et al.  Enforcing Meter in Finite-Length Markov Sequences , 2013, AAAI.

[10]  Yoshua Bengio,et al.  Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription , 2012, ICML.

[11]  Daniel Müllensiefen,et al.  Bayesian Model Selection for Harmonic Labelling , 2007 .

[12]  Gerhard Nierhaus,et al.  Algorithmic Composition: Paradigms of Automated Music Generation , 2008 .

[13]  François Pachet,et al.  Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence Finite-Length Markov Processes with Constraints , 2022 .

[14]  Eduardo Reck Miranda,et al.  Constraint programming systems for modeling music theories and composition , 2011, CSUR.