Instabilities in Convnets for Raw Audio

Abstract

What makes waveform-based deep learning so hard? Despite numerous attempts at training convolutional neural networks (convnets) for filterbank design, they often fail to outperform hand-crafted baselines. These baselines are linear time-invariant systems: as such, they can be approximated by convnets with wide receptive fields. Yet, in practice, gradient-based optimization leads to suboptimal approximations. In our article, we approach this phenomenon from the perspective of initialization. We present a theory of large deviations for the energy response of FIR filterbanks with random Gaussian weights. We find that deviations worsen for large filters and locally periodic input signals, which are both typical for audio signal processing applications. Numerical simulations align with our theory and suggest that the condition number of a convolutional layer follows a logarithmic scaling law between the number and length of the filters, which is reminiscent of discrete wavelet bases.

4 pages, 5 figures, 1 page appendix with mathematical proofs

References in corpus (6)

• Computational bioacoustics with deep learning: a review and roadmap
• Frame Theory for Signal Processing in Psychoacoustics
• A learning approach to the detection of gravitational wave transients
• The asymptotic distribution of the condition number for random circulant matrices
• Fitting Auditory Filterbanks with Multiresolution Neural Networks
• Preconditioning filter bank decompositions using structured normalized tight frames