Composing Multi-Instrumental Music with Recurrent Neural Networks

We propose a generative model for artificial composition of both classical and popular music with the goal of producing music as well as humans do. The problem is that music is based on a highly sophisticated hierarchical structure and it is hard to measure its quality automatically. Contrary to other’s work, we try to generate a symbolic representation of music with multiple different instruments playing simultaneously to cover a broader musical space. We train three modules based on LSTM networks to generate the music; a lot of effort is put into reducing the high complexity of multi-instrumental music representation by a thorough musical analysis. We believe that the proposed preprocessing techniques and symbolic representation constitute a useful resource for future research in this field.

[1]  Xiaoou Tang,et al.  Surpassing Human-Level Face Verification Performance on LFW with GaussianFace , 2014, AAAI.

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

[3]  Daniel D. Johnson,et al.  Generating Polyphonic Music Using Tied Parallel Networks , 2017, EvoMUSART.

[4]  J. Schmidhuber,et al.  A First Look at Music Composition using LSTM Recurrent Neural Networks , 2002 .

[5]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[6]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[7]  Gaëtan Hadjeres,et al.  Deep Learning Techniques for Music Generation - A Survey , 2017, ArXiv.

[8]  David Samuel,et al.  Artificial Composition of Multi-Instrumental Polyphonic Music , 2018 .

[9]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[10]  Adam M. Stark,et al.  Musicians and Machines: Bridging the Semantic Gap In Live Performance , 2011 .

[11]  Aran Nayebi,et al.  GRUV: Algorithmic Music Generation using Recurrent Neural Networks , 2015 .

[12]  V. Zenz,et al.  Automatic Chord Detection Incorporating Beat and Key Detection , 2007, 2007 IEEE International Conference on Signal Processing and Communications.

[13]  E. Clarke,et al.  Music and Consciousness: Philosophical, Psychological, and Cultural Perspectives , 2011 .

[14]  Lior Wolf,et al.  Using the Output Embedding to Improve Language Models , 2016, EACL.

[15]  Murray Campbell,et al.  Deep Blue , 2002, Artif. Intell..

[16]  Aaron C. Courville,et al.  Recurrent Batch Normalization , 2016, ICLR.

[17]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[18]  Vladlen Koltun,et al.  An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling , 2018, ArXiv.

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

[20]  Heiga Zen,et al.  WaveNet: A Generative Model for Raw Audio , 2016, SSW.

[21]  Daniele P. Radicioni,et al.  BREVE: An HMPerceptron-Based Chord Recognition System , 2010, Advances in Music Information Retrieval.

[22]  D. Temperley.  The Cognition of Basic Musical Structures , 2001 .

[23]  Kratarth Goel,et al.  Modeling temporal dependencies in data using a DBN-LSTM , 2015, 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA).