Timezone: »

Spline Filters For End-to-End Deep Learning
Randall Balestriero · Romain Cosentino · Herve Glotin · Richard Baraniuk

Wed Jul 11 08:50 AM -- 09:00 AM (PDT) @ Victoria
We propose to tackle the problem of end-to-end learning for raw waveforms signals by introducing learnable continuous time-frequency atoms. The derivation of these filters is achieved by first, 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 equip any Deep Neural Networks (DNNs) 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 high dimensional inputs ($>100000$) and the presence of multiple sources and soundscapes.

Author Information

Randall Balestriero (Rice University)
Romain Cosentino (Rice University)
Herve Glotin (Universite de Toulon)
Richard Baraniuk (OpenStax / Rice University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors