A Discriminative Model to Generate Melodies through Evolving LSTM Recurrent Neural Networks

Authors

  • Dr. Nanda Ashwin  Professor, Dept. of Information Science and Engineering, East Point College of Engineering and Technology, Bangalore, India
  • Uday Kumar Adusumilli  Product Support Analyst, Associate, Infor, Bangalore, India
  • Lakshmi Kurra  Student, Dept. of Information Science and Engineering, East Point College of Engineering and Technology, Bangalore, India
  • Prof. Kemparaju N  Head, Dept. of Information Science and Engineering, East Point College of Engineering and Technology, Bangalore, India

DOI:

https://doi.org/10.32628/IJSRSET219411

Keywords:

LSTM, Music Generation, Deep Learning, Recurrent Neural Networks, RNN, Discriminative Model, Evolving LSTM, Evolving LSTM RNN

Abstract

The paper describes a method that uses evolving LSTM recurrent neural networks to generate melodic music through a discriminative model. The approach enclosed has achieved an accuracy level of over 90%, thus enabling our model to understand & generate music as per the input parameters. The input expected from the user is minimal and can be provided by a layman. The experiments presented here demonstrate how LSTM can successfully learn a form of training music data and compose a novel (and pleasing) melody based on that style of training. LSTM can play melodies with good timing and appropriate structure if the parameters have been set appropriately. The RNN Model presented in this paper leverages the benefits of LSTM networks and demonstrates how this feat can be achieved.

References

  1. Breuleux, O., Bengio, Y., and Vincent, P. (2011). Quickly generating representative samples from an RBM-derived process. Neural Computation, 23 (8), 20532073.
  2. Karpathy, A., The unreasonable effectiveness of recurrent neural networks, 2015.
  3. Eck, D. and Schmidhuber, J. Finding temporal structure in music: Blues improvisation with LSTM recurrent networks. In NNSP, pp. 747–756, 2002.
  4. D. A. and M. Clements. Melody spotting using hidden markov models. In J. S. Downie and D. Bainbridge, editors, Proceedings of the 2nd Annual International Symposium on Music Information Retrieval (ISMIR), pages 109–117, Indiana University, Bloomington, Indiana, October 2001.
  5. J. P. Bello, L. Daudet, and M. B. Sandler. Time-domain polyphonic transcription using self-generating databases. In Proceedings of the 112th Convention of the Audio Engineering Society, Munich, Germany, May 2002.
  6. D. Temperley, A probabilistic model of music perception, in: Proceedings of the 7th Conference on Music Information Retrieval, Victoria, Canada, 2006.
  7. van den Oord, A., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A. and Kavukcuoglu, K., 2016. WaveNet: A generative model for raw audio.arXiv preprint arXiv:1609.03499.
  8. Daniel Johnson, Composing Music With Recurrent Neural Networks, 2015
  9. Theis, L., Oord, A.V.D. and Bethge, M., 2015. A note on the evaluation of generative models. arXiv :1511.01844.
  10. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. and Bengio, Y., 2014. Generative adversarial nets In Advances in Neural Information Processing Systems (pp. 2672-2680).
  11. Eck, D., Schmidhuber, J. (2002) A First Look at Music Composition using LSTM Recurrent Neural Networks. Technical Report No. IDSIA-07-02
  12. Sutskever, I., Hinton, G., and Taylor, G. The recurrent temporal restricted Boltzmann machine. In NIPS 20, pp. 1601–1608, 2008.
  13. Antokoletz, E. (1981). The Musical Language of Bartok’s 14 Bagatelles for Piano. Tempo, Vol. 137.
  14. Allen Huang and Raymond Wu. Deep learning for music, June 2016. arXiv:1606.04930v1.
  15. Chun-Chi J. Chen and Risto Miikkulainen. Creating melodies with evolving recurrent neural networks. Proceedings of the 2001 International Joint Conference on Neural Networks, 2001.
  16. J.-F. Paiement, D. Eck, S. Bengio, Probabilistic melodic harmonization, in: Proceedings of the 19th Canadian Conference on Artificial Intelligence, Springer, 2006.
  17. V. Lavrenko, J. Pickens, Polyphonic music modeling with random fields, in: Proceedings of ACM Multimedia, Berkeley, CA, 2003.
  18. J. P. Bello, J. Pickens, A robust mid-level representation for harmonic content in music signals, in: Proceedings of the Sixth International Conference on Music Information Retrieval, London, 2005.
  19. Franklin, Judy A. Recurrent neural networks for music computation. INFORMS Journal on Computing, 18(3):321–338, 2006.
  20. Godbole, Shantanu and Sarawagi, Sunita. Discriminative methods for multi-labeled classification. In Advances in Knowledge Discovery and Data Mining, pp. 22–30. Springer, 2004.
  21. Mozer, Michael C. Neural network music composition by prediction: Exploring the benefits of psychoacoustic constraints and multi-scale processing. Connection Science, 6(2-3):247–280, 1994.
  22. Platt. Fast training of support vector machines using sequential minimal optimization. In B. Scholkopf, C. J. C. Burges, and A. J. Smola, editors, Advances in Kernel Methods – Support Vector Learning, pages 185–208. MIT Press, Cambridge, MA, 1998.
  23. Rossi, G. Girolami, and M. Leca. Identification of polyphonic piano signals. Acustica, 83:1077–1084, 1997.
  24. Ryyn¨anen and A. Klapuri. Polyphonic music transcription using note event modeling. In Proc. IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, New Paltz, October 2005.
  25. Schlkopf, J.C. Platt, J. Shawe-Taylor, A.J. Smola, and R.C. Williamson. Estimating the support of a high-dimensional distribution. Neural Computation, 13(7):1443–1471, 2001. A.D. Sterian. Model-based Segmentation of Time-Frequency Images for Musical Transcription. PhD thesis, University of Michigan, 1999.
  26. J.P. Bello, L. Daudet, and M. Sandler. Time-domain polyphonic transcription using self-generating databases. In Proc. 112th Convention of the Audio Engineering Society, Munich, May 2002.
  27. A.T. Cemgil, H.J. Kappen, and D. Barber. A generative model for music transcription. To Appear in IEEE Transactions on Speech and Audio Processing, 2005.
  28. S. Dixon. On the computer recognition of solo piano music. In Proc. Australasian Computer Music Conference, Brisbane, 2000.
  29. D. Ellis and G. Poliner. Classification-based melody transcription. Machine Learning, 2006.
  30. S. Godsill and M. Davy. Bayesian harmonic models for musical pitch estimation and analysis. In Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Orlando, 2002.
  31. K. Kashino and S. Godsill. Bayesian estimation of simultaneous musical notes based on frequency domain modelling. In Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Montreal, 2004.

International Journal of Scientific Research in Science, Engineering and Technology

Downloads

Published

2021-07-30

Issue

Volume 9, Issue 4, July-August-2021

Section

Research Articles

License

Copyright (c) IJSRSET

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Dr. Nanda Ashwin, Uday Kumar Adusumilli, Lakshmi Kurra, Prof. Kemparaju N "A Discriminative Model to Generate Melodies through Evolving LSTM Recurrent Neural Networks" International Journal of Scientific Research in Science, Engineering and Technology (IJSRSET), Print ISSN : 2395-1990, Online ISSN : 2394-4099, Volume 9, Issue 4, pp.52-59, July-August-2021. Available at doi : https://doi.org/10.32628/IJSRSET219411