Generative Fourier-Based Auto-encoders: Preliminary Results

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12566)


This paper presents a new general framework for turning any auto-encoder into a generative model. Here, we focus on a specific instantiation of the auto-encoder that consists of the Short Time Fourier Transform as an encoder, and a composition of the Griffin-Lim Algorithm and the pseudo inverse of the Short Time Fourier Transform as a decoder. In order to allow sampling from this model, we propose to use the probabilistic Principal Component Analysis. We show preliminary results on the UrbanSound8K Dataset.


Auto-encoders Generative modelling Fourier Transform 


  1. 1.
    Bengio, Y., et al.: Learning deep architectures for AI. Found. Trends ® Mach. Learn. 2(1), 1–127 (2009)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Ghosh, P., Sajjadi, M.S., Vergari, A., Black, M., Schölkopf, B.: From variational to deterministic autoencoders. arXiv preprint arXiv:1903.12436 (2019)
  3. 3.
    Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)Google Scholar
  4. 4.
    Kalchbrenner, N., et al.: Efficient neural audio synthesis. In: International Conference on Machine Learning, pp. 2410–2419 (2018)Google Scholar
  5. 5.
    Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013)
  6. 6.
    Oord, A.V.D., et al.: Wavenet: a generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016)
  7. 7.
    Salamon, J., Jacoby, C., Bello, J.P.: A dataset and taxonomy for urban sound research. In: Proceedings of the 22nd ACM International Conference on Multimedia. MM 2014, New York, NY, USA, pp. 1041–1044. Association for Computing Machinery (2014)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Vrije Universiteit AmsterdamAmsterdamThe Netherlands

Personalised recommendations