ISAC: An Invertible and Stable Auditory Filter Bank with Customizable Kernels for ML Integration

Daniel Haider, Felix Perfler, Peter Balazs, Clara Hollomey, Nicki Holighaus

Session: General

Keywords: filter banks, invertibility, stability, auditory, convolutional neural networks

TL;DR: We introduce a stable and invertible, perceptually-motivated filter bank with restricted kernel sizes, meant to be used in a machine learning paradigm.

Abstract:

This paper introduces ISAC, an invertible and stable, perceptually-motivated filter bank that is specifically designed to be integrated into machine learning paradigms. More precisely, the center frequencies and bandwidths of the filters are chosen to follow a non-linear, auditory frequency scale, the filter kernels have user-defined maximum temporal support and may serve as learnable convolutional kernels, and there exists a corresponding filter bank such that both form a perfect reconstruction pair. ISAC provides a powerful and user-friendly audio front-end suitable for any application, including analysis-synthesis schemes.

Submission Number: 115