Computer-aided music composition with LSTM neural network and chaotic inspiration

In this paper a new neural network system for composition of melodies is proposed. The Long Short-Term Memory (LSTM) neural network is adopted as the neural network model. We include an independent melody as an additional input in order to provide an inspiration source to the network. This melody is given by a chaotic composition algorithm and works as an inspiration to the network enhancing the subjective measure of the composed melodies. As the chaotic system we use the Hénon map with two variables, which are mapped to pitch and rhythm. We adopt a measure to conduct the degree of melodiousness (Euler's gradus suavitatis) of the output melody, which is compared with a reference value. Varying a specific parameter of the chaotic system, we can control the complexity of the chaotic melody. The system runs until the degree of melodiousness falls within a predetermined range.

[1]  Yoshua Bengio,et al.  Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies , 2001 .

[2]  D.C. Correa,et al.  Composing Music with BPTT and LSTM Networks: Comparing Learning and Generalization Aspects , 2008, 2008 11th IEEE International Conference on Computational Science and Engineering - Workshops.

[3]  T. Eerola,et al.  Expectancy-Based Model of Melodic Complexity , 2000 .

[4]  Liang Zhao,et al.  Characterizing chaotic melodies in automatic music composition. , 2010, Chaos.

[5]  F. Gers,et al.  Long short-term memory in recurrent neural networks , 2001 .

[6]  Barak A. Pearlmutter Gradient calculations for dynamic recurrent neural networks: a survey , 1995, IEEE Trans. Neural Networks.

[7]  Jürgen Schmidhuber,et al.  Finding temporal structure in music: blues improvisation with LSTM recurrent networks , 2002, Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing.

[8]  Risto Miikkulainen,et al.  Creating melodies with evolving recurrent neural networks , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[9]  F. Richard Moore,et al.  Elements of computer music , 1990 .

[10]  Judy A. Franklin,et al.  Recurrent Neural Networks for Music Computation , 2006, INFORMS J. Comput..

[11]  Roseli A. Francelin Romero,et al.  Generation of composed musical structures through recurrent neural networks based on chaotic inspiration , 2011, The 2011 International Joint Conference on Neural Networks.

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