Spline Filters For End-to-End Deep Learning

Abstract : We propose to tackle the problem of end-to-end learning for raw waveform signals by introducing learnable continuous time-frequency atoms. The derivation of these filters is achieved by defining a functional space with a given smoothness order and boundary conditions. From this space, we derive the parametric analytical filters. Their differentiability property allows gradient-based optimization. As such, one can utilize any Deep Neural Network (DNN) with these filters. This enables us to tackle in a front-end fashion a large scale bird detection task based on the freefield1010 dataset known to contain key challenges , such as the dimensionality of the inputs data (> 100, 000) and the presence of additional noises: multiple sources and soundscapes.
Complete list of metadatas

Cited literature [35 references]  Display  Hide  Download

Contributor : Herve Glotin <>
Submitted on : Saturday, September 22, 2018 - 6:07:31 PM
Last modification on : Thursday, February 7, 2019 - 4:53:40 PM
Long-term archiving on : Sunday, December 23, 2018 - 1:11:07 PM


Files produced by the author(s)


  • HAL Id : hal-01879266, version 1



Randall Balestriero, Romain Cosentino, Hervé Glotin, Richard Baraniuk. Spline Filters For End-to-End Deep Learning. 35th International Conference on Machine Learning, Jul 2018, stockholm, Sweden. ⟨hal-01879266⟩



Record views


Files downloads