Skip to main content
SpringerLink
Log in

A novel U-Net with dense block for drum signal separation from polyphonic music signal mixture

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

Deep neural network algorithms have shown promising results for music source signal separation. Most existing methods rely on deep networks, where billions of parameters need to be trained. In this paper, we propose a novel autoencoder framework with a reduced number of parameters to separate the drum signal component from a music signal mixture. A denoising autoencoder with a U-Net architecture and direct skip connections was employed. A dense block is included in the bottleneck of the autoencoder stage. This technique was tested on both demixing secret data (DSD) and the MUSDB database. The source-to-distortion ratio (SDR) for the proposed method was at par with that of other state-of-the-art methods, whereas the number of parameters required was quite low, making it computationally more efficient. The experiment performed using the proposed method to separate drum signal yielded an average SDR of 5.71 on DSD and 6.45 on MUSDB database while using only 0.32 million parameters.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Notes

  1. https://sigsep.github.io/datasets/dsd100.html.

  2. https://doi.org/10.5281/zenodo.1117372.

  3. https://github.com/sigsep/sigsep-mus-eval.

  4. https://gitlab.inria.fr/bass-db/peass.

References

  1. Muller, M., Ellis, D.P., Klapuri, A., Richard, G.: Signal processing for music analysis. IEEE J. Sel. Top. Signal Process. 5(6), 1088–1110 (2011)

    Article  Google Scholar 

  2. Hyvarinen, A., Oja, E.: Independent component analysis: algorithms and applications. Neural Netw. 13(4–5), 411–430 (2000)

    Article  Google Scholar 

  3. Virtanen, T.: Monaural sound source separation by nonnegative matrix factorization with temporal continuity and sparseness criteria. IEEE Trans. Audio Speech Lang. Process. 15(3), 1066–1074 (2007)

    Article  Google Scholar 

  4. Gillet, O., Richard, G.: Transcription and separation of drum signals from polyphonic music. IEEE Trans. Audio Speech Lang. Process. 16(3), 529–540 (2008)

    Article  Google Scholar 

  5. Kotti, M., Ververidis, D., Evangelopoulos, G., Panagakis, I., Kotropoulos, C., Maragos, P., Pitas, I.: Audio-assisted movie dialogue detection. IEEE Trans. Circuits Syst. Video Technol. 18(11), 1618–1627 (2008)

    Article  Google Scholar 

  6. Helen, M., Virtanen, T.: Separation of drums from polyphonic music using non-negative matrix factorization and support vector machine. In: 2005 13th European Signal Processing Conference, pp. 1–4. IEEE (2005)

  7. Srinivasan, S., Roman, N., Wang, D.: Binary and ratio time-frequency masks for robust speech recognition. Speech Commun. 48(11), 1486–1501 (2006)

    Article  Google Scholar 

  8. Kadandale, V.S., Montesinos, J.F., Haro, G., Gómez, E.: Multi-channel U-NET for music source separation. In: 2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP), pp. 1–6. IEEE (2020)

  9. Stoller, D., Ewert, S., Dixon, S.: Wave-U-Net: a multi-scale neural network for end-to-end audio source separation. arXiv preprint arXiv:1806.03185 (2018)

  10. Samuel, D., Ganeshan, A., Naradowsky, J.: Meta-learning extractors for music source separation. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 816–820. IEEE (2020)

  11. Défossez, A., Usunier, N., Bottou, L., Bach, F.: Music source separation in the waveform domain. arXiv preprint arXiv:1911.13254 (2019)

  12. Huang, P.-S., Kim, M., Hasegawa-Johnson, M., Smaragdis, P.: Joint optimization of masks and deep recurrent neural networks for monaural source separation. IEEE/ACM Trans. Audio Speech Lang. Process. 23(12), 2136–2147 (2015)

    Article  Google Scholar 

  13. Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)

  14. Uhlich, S., Giron, F., Mitsufuji, Y.: Deep neural network based instrument extraction from music. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2135–2139. IEEE (2015)

  15. Chandna, P., Miron, M., Janer, J., Gómez, E.: Monoaural audio source separation using deep convolutional neural networks. In: International Conference on Latent Variable Analysis and Signal Separation, pp. 258–266. Springer (2017)

  16. Grais, E.M., Plumbley, M.D.: Single channel audio source separation using convolutional denoising autoencoders. In: 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP), pp. 1265–1269. IEEE (2017)

  17. Jansson, A., Humphrey, E., Montecchio, N., Bittner, R., Kumar, A., Weyde, T.: Singing voice separation with deep U-Net convolutional networks (2017)

  18. Liu, J.-Y., Yang, Y.-H.: Denoising auto-encoder with recurrent skip connections and residual regression for music source separation. In: 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 773–778. IEEE (2018)

  19. Uhlich, S., Porcu, M., Giron, F., Enenkl, M., Kemp, T., Takahashi, N., Mitsufuji, Y.: Improving music source separation based on deep neural networks through data augmentation and network blending. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 261–265. IEEE (2017)

  20. Takahashi, N., Mitsufuji, Y.: Multi-scale multi-band densenets for audio source separation. In: 2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), pp. 21–25. IEEE (2017)

  21. Takahashi, N., Goswami, N., Mitsufuji, Y.: Mmdenselstm: an efficient combination of convolutional and recurrent neural networks for audio source separation. In: 2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC), pp. 106–110. IEEE (2018)

  22. Satya, M.F., Suyanto, S.: Music source separation using generative adversarial network and U-Net. In: 2020 8th International Conference on Information and Communication Technology (ICoICT), pp. 1–6. IEEE (2020)

  23. Li, T., Chen, J., Hou, H., Li, M.: Sams-Net: a sliced attention-based neural network for music source separation. In: 2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP), pp. 1–5. IEEE (2021)

  24. Stöter, F.-R., Uhlich, S., Liutkus, A., Mitsufuji, Y.: Open-Unmix—a reference implementation for music source separation. J Open Source Softw 4, 1667 (2019)

    Article  Google Scholar 

  25. Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-assisted Intervention, pp. 234–241. Springer (2015)

  26. Rafii, Z., Liutkus, A., Stöter, F.-R., Mimilakis, S.I., Bittner, R.: MUSDB18—a corpus for music separation (2017)

  27. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)

  28. He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026–1034 (2015)

  29. Vincent, E., Gribonval, R., Févotte, C.: Performance measurement in blind audio source separation. IEEE Trans. Audio Speech Lang. Process. 14(4), 1462–1469 (2006)

    Article  Google Scholar 

  30. Stöter, F.-R., Liutkus, A., Ito, N.: The 2018 signal separation evaluation campaign. In: International Conference on Latent Variable Analysis and Signal Separation, pp. 293–305. Springer (2018)

  31. You, J., Reiter, U., Hannuksela, M.M., Gabbouj, M., Perkis, A.: Perceptual-based quality assessment for audio–visual services: a survey. Signal Process. Image Commun. 25(7), 482–501 (2010)

    Article  Google Scholar 

  32. Emiya, V., Vincent, E., Harlander, N., Hohmann, V.: Subjective and objective quality assessment of audio source separation. IEEE Trans. Audio Speech Lang. Process. 19(7), 2046–2057 (2011)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Model Engineering College, Cochin University of Science and Technology, Kochi, Kerala, India

    E. Vinitha George

  2. St. Joseph’s College of Engineering and Technology, Palai, Kerala, India

    V. P. Devassia

Authors
  1. E. Vinitha George
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. V. P. Devassia
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to E. Vinitha George.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Vinitha George, E., Devassia, V.P. A novel U-Net with dense block for drum signal separation from polyphonic music signal mixture. SIViP 17, 627–633 (2023). https://doi.org/10.1007/s11760-022-02269-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-022-02269-1

Keywords

Search

Navigation