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.
KeywordsMusic generation Graphical models Belief propagation Sampling Web-service User interaction
This research is conducted within the Flow Machines project which received funding from the European Research Council under the European Union’s Seventh Framework Programme (FP/2007-2013)/ERC Grant Agreement n. 291156. We thank Benoît Carré and the team of the musical Beyond the Fence for their insightful comments in using the system. We thank Fiammetta Ghedini for creating the associated website with audio and video examples.
- 1.Anders, T., Miranda, E.R.: Constraint programming systems for modeling music theories and composition. ACM Comput. Surv. 43(4), 30:1–30:38 (2011)Google Scholar
- 3.Boulanger-Lewandowski, N., Bengio, Y., Vincent, P.: Modeling temporal dependencies in high-dimensional sequences: application to polyphonic music generation and transcription, pp. 1159–1166 (2012)Google Scholar
- 5.Colton, S., Llano, M.T., Hepworth, R., Charnley, J., Gale, C.V., Baron, A., Pachet, F., Roy, P., Gervás, P., Collins, N., Sturm, B., Weyde, T., Wolff, D., Lloyd, J.: The Beyond the Fence musical and computer says show documentary. In: 7th International Conference on Computational Creativity (ICCC 2016), Paris, France, June 2016Google Scholar
- 9.Pachet, F., Roy, P., Barbieri, G.: Finite-length Markov processes with constraints. In: IJCAI, pp. 635–642 (2011)Google Scholar
- 10.Pachet, F., Suzda, J., Martinez, D.: A comprehensive online database of machine-readable lead-sheets for jazz standards. In: de Souza Britto Jr., A., Gouyon, F., Dixon, S.(ed.) ISMIR, pp. 275–280 (2013)Google Scholar
- 11.Pachet, F.: Flow-Machines: CP techniques to model style in music and text. ACP (Association for Constraint Programming) (2015). http://www.a4cp.org/node/1066
- 12.Papadopoulos, A., Pachet, F., Roy, P., Sakellariou, J.: Exact sampling for regular and Markov constraints with belief propagation. In: Pesant, G. (ed.) CP 2015. LNCS, vol. 9255, pp. 341–350. Springer, Heidelberg (2015)Google Scholar
- 15.Roy, P., Pachet, F.: Enforcing meter in finite-length Markov sequences. In: des Jardins, M., Littman, M.L. (ed.) AAAI. AAAI Press (2013)Google Scholar