Skip to main content
SpringerLink
Log in

Conditional Drums Generation Using Compound Word Representations

  • Conference paper
  • First Online:
Artificial Intelligence in Music, Sound, Art and Design (EvoMUSART 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13221))

Abstract

The field of automatic music composition has seen great progress in recent years, specifically with the invention of transformer-based architectures. When using any deep learning model which considers music as a sequence of events with multiple complex dependencies, the selection of a proper data representation is crucial. In this paper, we tackle the task of conditional drums generation using a novel data encoding scheme inspired by the Compound Word representation, a tokenization process of sequential data. Therefore, we present a sequence-to-sequence architecture where a Bidirectional Long short-term memory (BiLSTM) Encoder receives information about the conditioning parameters (i.e., accompanying tracks and musical attributes), while a Transformer-based Decoder with relative global attention produces the generated drum sequences. We conducted experiments to thoroughly compare the effectiveness of our method to several baselines. Quantitative evaluation shows that our model is able to generate drums sequences that have similar statistical distributions and characteristics to the training corpus. These features include syncopation, compression ratio, and symmetry among others. We also verified, through a listening test, that generated drum sequences sound pleasant, natural and coherent while they “groove” with the given accompaniment.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 109.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 139.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    https://github.com/chromamorph/omnisia-recursia-rrt-mml-2019.

  2. 2.

    https://github.com/melkor169/CP_Drums_Generation.

References

  1. Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. In: OSDI, vol. 16, pp. 265–283 (2016)

    Google Scholar 

  2. Agres, K., Forth, J., Wiggins, G.A.: Evaluation of musical creativity and musical metacreation systems. Comput. Entertain. (CIE) 14(3), 1–33 (2016)

    Article  Google Scholar 

  3. Briot, J.P., Hadjeres, G., Pachet, F.D.: Deep Learning Techniques for Music Generation. Springer, Cham (2020). https://doi.org/10.1007/978-3-319-70163-9

  4. Bruford, F., McDonald, S., Sandler, M.: jaki: user-controllable generation of drum patterns using an LSTM encoder-decoder and deep reinforcement learning. In: The 2020 Joint Conference on AI Music Creativity (2020)

    Google Scholar 

  5. Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv:1406.1078 (2014)

  6. Cho, Y.H., Lim, H., Kim, D.W., Lee, I.K.: Music emotion recognition using chord progressions. In: 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 002588–002593. IEEE (2016)

    Google Scholar 

  7. Choi, K., Park, J., Heo, W., Jeon, S., Park, J.: Chord conditioned melody generation with transformer based decoders. IEEE Access 9, 42071–42080 (2021)

    Article  Google Scholar 

  8. Chou, Y.H., Chen, I., Chang, C.J., Ching, J., Yang, Y.H., et al.: MidiBERT-Piano: large-scale pre-training for symbolic music understanding. arXiv preprint arXiv:2107.05223 (2021)

  9. Chuan, C.H., Herremans, D.: Modeling temporal tonal relations in polyphonic music through deep networks with a novel image-based representation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)

    Google Scholar 

  10. Deliège, I., Wiggins, G.A.: Musical Creativity: Multidisciplinary Research in Theory and Practice. Psychology Press (2006)

    Google Scholar 

  11. Dong, H.W., Hsiao, W.Y., Yang, L.C., Yang, Y.H.: MuseGAN: multi-track sequential generative adversarial networks for symbolic music generation and accompaniment. In: 32nd AAAI Conference on Artificial Intelligence (2018)

    Google Scholar 

  12. Gillick, J., Roberts, A., Engel, J., Eck, D., Bamman, D.: Learning to groove with inverse sequence transformations. In: International Conference on Machine Learning, pp. 2269–2279. PMLR (2019)

    Google Scholar 

  13. Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 18(5–6), 602–610 (2005)

    Article  Google Scholar 

  14. Hadjeres, G., Pachet, F., Nielsen, F.: DeepBach: a steerable model for Bach chorales generation. In: International Conference on Machine Learning, pp. 1362–1371. PMLR (2017)

    Google Scholar 

  15. Herremans, D., Chew, E.: MorpheuS: generating structured music with constrained patterns and tension. IEEE Trans. Affect. Comput. 10(4), 510–523 (2017)

    Article  Google Scholar 

  16. Herremans, D., Chuan, C.H., Chew, E.: A functional taxonomy of music generation systems. ACM Comput. Surv. 50(5), 1–30 (2017)

    Article  Google Scholar 

  17. Herremans, D., Sörensen, K.: Composing fifth species counterpoint music with a variable neighborhood search algorithm. Exp. Syst. Appl. 40(16), 6427–6437 (2013)

    Article  Google Scholar 

  18. Hsiao, W.Y., Liu, J.Y., Yeh, Y.C., Yang, Y.H.: Compound word transformer: learning to compose full-song music over dynamic directed hypergraphs. arXiv preprint arXiv:2101.02402 (2021)

  19. Huang, C.Z.A., et al.: Music transformer: generating music with long-term structure. In: International Conference on Learning Representations (2018)

    Google Scholar 

  20. Huang, Y.S., Yang, Y.H.: Pop music transformer: beat-based modeling and generation of expressive pop piano compositions. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1180–1188 (2020)

    Google Scholar 

  21. Hung, H.T., Ching, J., Doh, S., Kim, N., Nam, J., Yang, Y.H.: EMOPIA: a multi-modal pop piano dataset for emotion recognition and emotion-based music generation. arXiv preprint arXiv:2108.01374 (2021)

  22. Hutchings, P.: Talking drums: generating drum grooves with neural networks. arXiv:1706.09558 (2017)

  23. Kaliakatsos–Papakostas, M.A., Floros, A., Vrahatis, M.N.: evoDrummer: deriving rhythmic patterns through interactive genetic algorithms. In: Machado, P., McDermott, J., Carballal, A. (eds.) EvoMUSART 2013. LNCS, vol. 7834, pp. 25–36. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-36955-1_3

    Chapter  Google Scholar 

  24. Kaliakatsos-Papakostas, M.A., Floros, A., Kanellopoulos, N., Vrahatis, M.N.: Genetic evolution of L and FL-systems for the production of rhythmic sequences. In: Proceedings of the 14th Annual Conference Companion on Genetic and Evolutionary Computation, pp. 461–468 (2012)

    Google Scholar 

  25. Karbasi, S.M., Haug, H.S., Kvalsund, M.K., Krzyzaniak, M.J., Torresen, J.: A generative model for creating musical rhythms with deep reinforcement learning. In: 2nd Conference on AI Music Creativity (2021)

    Google Scholar 

  26. Lattner, S., Grachten, M.: High-level control of drum track generation using learned patterns of rhythmic interaction. arXiv:1908.00948 (2019)

  27. Liu, H.M., Yang, Y.H.: Lead sheet generation and arrangement by conditional generative adversarial network. In: 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 722–727. IEEE (2018)

    Google Scholar 

  28. Longuet-Higgins, H.C., Lee, C.S.: The rhythmic interpretation of monophonic music. Music. Percept. 1(4), 424–441 (1984)

    Article  Google Scholar 

  29. Makris, D., Agres, K.R., Herremans, D.: Generating lead sheets with affect: a novel conditional seq2seq framework. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN) (2021)

    Google Scholar 

  30. Makris, D., Kaliakatsos-Papakostas, M., Karydis, I., Kermanidis, K.L.: Combining LSTM and feed forward neural networks for conditional rhythm composition. In: Boracchi, G., Iliadis, L., Jayne, C., Likas, A. (eds.) EANN 2017. CCIS, vol. 744, pp. 570–582. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-65172-9_48

    Chapter  Google Scholar 

  31. Makris, D., Kaliakatsos-Papakostas, M., Karydis, I., Kermanidis, K.L.: Conditional neural sequence learners for generating drums’ rhythms. Neural Comput. Appl. 31(6), 1793–1804 (2019)

    Article  Google Scholar 

  32. Meredith, D.: COSIATEC and SIATECCOMPRESS: pattern discovery by geometric compression. In: Proceedings of the ISMIR (2013)

    Google Scholar 

  33. Nuttall, T., Haki, B., Jorda, S.: Transformer neural networks for automated rhythm generation. In: International Conference on New Interfaces for Musical Expression (2021)

    Google Scholar 

  34. Oore, S., Simon, I., Dieleman, S., Eck, D., Simonyan, K.: This time with feeling: learning expressive musical performance. Neural Comput. Appl. 32(4), 955–967 (2020)

    Article  Google Scholar 

  35. Papadopoulos, A., Roy, P., Pachet, F.: Assisted lead sheet composition using FlowComposer. In: Rueher, M. (ed.) CP 2016. LNCS, vol. 9892, pp. 769–785. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-44953-1_48

    Chapter  Google Scholar 

  36. Papadopoulos, G., Wiggins, G.: AI methods for algorithmic composition: a survey, a critical view and future prospects. In: AISB Symposium on Musical Creativity, Edinburgh, UK, pp. 110–117 (1999)

    Google Scholar 

  37. Raffel, C.: Learning-based methods for comparing sequences, with applications to audio-to-midi alignment and matching. Ph.D. thesis, Columbia University (2016)

    Google Scholar 

  38. Randel, D.M.: The Harvard Concise Dictionary of Music and Musicians. Harvard University Press (1999)

    Google Scholar 

  39. Schreiber, H.: Improving genre annotations for the million song dataset. In: ISMIR, pp. 241–247 (2015)

    Google Scholar 

  40. Sioros, G., Holzapfel, A., Guedes, C.: On measuring syncopation to drive an interactive music system. In: 13th International Society for Music Information Retrieval Conference, ISMIR 2012, Porto, Portugal, pp. 283–288 (2012)

    Google Scholar 

  41. Tan, H.H., Herremans, D.: Music FaderNets: controllable music generation based on high-level features via low-level feature modelling. In: ISMIR (2020)

    Google Scholar 

  42. Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)

    Google Scholar 

  43. Wright, M., Berdahl, E.: Towards machine learning of expressive microtiming in Brazilian drumming. In: ICMC (2006)

    Google Scholar 

  44. Wu, S.L., Yang, Y.H.: The Jazz Transformer on the front line: exploring the shortcomings of AI-composed music through quantitative measures. arXiv preprint arXiv:2008.01307 (2020)

  45. Zixun, G., Makris, D., Herremans, D.: Hierarchical recurrent neural networks for conditional melody generation with long-term structure. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN) (2021)

    Google Scholar 

Download references

Acknowledgements

This work is supported by Singapore Ministry of Education Grant no. MOE2018-T2-2-161 and the Merlion PHC Campus France program.

Author information

Authors and Affiliations

  1. Information Systems Technology and Design, Singapore University of Technology and Design, Singapore, Singapore

    Dimos Makris, Guo Zixun & Dorien Herremans

  2. Institute for Language and Speech Processing, R.C. “Athena”, Athens, Greece

    Maximos Kaliakatsos-Papakostas

Authors
  1. Dimos Makris
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Guo Zixun
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Maximos Kaliakatsos-Papakostas
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Dorien Herremans
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Dimos Makris .

Editor information

Editors and Affiliations

  1. University of Coimbra, Coimbra, Portugal

    Tiago Martins

  2. University of A Coruña, A Coruña, Spain

    Nereida Rodríguez-Fernández

  3. University of Coimbra, Coimbra, Portugal

    Sérgio M. Rebelo

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Makris, D., Zixun, G., Kaliakatsos-Papakostas, M., Herremans, D. (2022). Conditional Drums Generation Using Compound Word Representations. In: Martins, T., Rodríguez-Fernández, N., Rebelo, S.M. (eds) Artificial Intelligence in Music, Sound, Art and Design. EvoMUSART 2022. Lecture Notes in Computer Science, vol 13221. Springer, Cham. https://doi.org/10.1007/978-3-031-03789-4_12

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-03789-4_12

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-03788-7

  • Online ISBN: 978-3-031-03789-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation