DeepBach: a Steerable Model for Bach Chorales Generation

This paper introduces DeepBach, a graphical model aimed at modeling polyphonic music and specifically hymn-like pieces. We claim that, after being trained on the chorale harmonizations by Johann Sebastian Bach, our model is capable of generating highly convincing chorales in the style of Bach. DeepBach's strength comes from the use of pseudo-Gibbs sampling coupled with an adapted representation of musical data. This is in contrast with many automatic music composition approaches which tend to compose music sequentially. Our model is also steerable in the sense that a user can constrain the generation by imposing positional constraints such as notes, rhythms or cadences in the generated score. We also provide a plugin on top of the MuseScore music editor making the interaction with DeepBach easy to use.

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

[2]  R. A. Bradley,et al.  RANK ANALYSIS OF INCOMPLETE BLOCK DESIGNS THE METHOD OF PAIRED COMPARISONS , 1952 .

[3]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[4]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Jun Zhu,et al.  Modelling High-Dimensional Sequences with LSTM-RTRBM: Application to Polyphonic Music Generation , 2015, IJCAI.

[6]  J. Besag.  Statistical Analysis of Non-Lattice Data , 1975 .

[7]  Marija Vucelja.  Lifting -- A nonreversible Markov chain Monte Carlo Algorithm , 2014 .

[8]  Vittorio Loreto,et al.  Maximum entropy models capture melodic styles , 2016, Scientific Reports.

[9]  Wolfram Menzel,et al.  HARMONET: A Neural Net for Harmonizing Chorales in the Style of J. S. Bach , 1991, NIPS.

[10]  Geraint A. Wiggins,et al.  Multiple Viewpoint Systems: Time Complexity and the Construction of Domains for Complex Musical Viewpoints in the Harmonization Problem , 2013 .

[11]  Christopher Ariza,et al.  Music21: A Toolkit for Computer-Aided Musicology and Symbolic Music Data , 2010, ISMIR.

[12]  Christopher K. I. Williams,et al.  Harmonising Chorales by Probabilistic Inference , 2004, NIPS.

[13]  E. Aurell,et al.  Improved contact prediction in proteins: using pseudolikelihoods to infer Potts models. , 2012, Physical review. E, Statistical, nonlinear, and soft matter physics.

[14]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[15]  David Maxwell Chickering,et al.  Dependency Networks for Inference, Collaborative Filtering, and Data Visualization , 2000, J. Mach. Learn. Res..

[16]  Marc'Aurelio Ranzato,et al.  Learning Longer Memory in Recurrent Neural Networks , 2014, ICLR.

[17]  Christopher De Sa,et al.  Ensuring Rapid Mixing and Low Bias for Asynchronous Gibbs Sampling , 2016, ICML.

[18]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[19]  Edward H Ip,et al.  Behaviour of the Gibbs sampler when conditional distributions are potentially incompatible , 2015, Journal of statistical computation and simulation.

[20]  Xiangang Li,et al.  Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recognition , 2014, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[21]  Kemal Ebcioglu,et al.  An Expert System for Harmonizing Four-Part Chorales , 1988, ICMC.

[22]  R. A. Bradley,et al.  Rank Analysis of Incomplete Block Designs: I. The Method of Paired Comparisons , 1952 .

[23]  A. Agresti,et al.  Categorical Data Analysis , 1991, International Encyclopedia of Statistical Science.

[24]  Vittorio Loreto,et al.  Maximum Entropy Model for Melodic Patterns , 2015 .

[25]  Gaëtan Hadjeres,et al.  Style Imitation and Chord Invention in Polyphonic Music with Exponential Families , 2016, ArXiv.

[26]  Anthony Unwin,et al.  Reversibility and Stochastic Networks , 1980 .

[27]  Razvan Pascanu,et al.  How to Construct Deep Recurrent Neural Networks , 2013, ICLR.

[28]  François Pachet,et al.  Assisted Lead Sheet Composition Using FlowComposer , 2016, CP.

[29]  Darrell Conklin,et al.  Music Generation from Statistical Models of Harmony , 2016 .

[30]  Barry C. Arnold,et al.  PSEUDOLIKELIHOOD ESTIMATION : SOME EXAMPLES , 2016 .