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

TL;DR

ISAC is a novel invertible and stable auditory filter bank designed for seamless integration into machine learning, featuring customizable kernels, perceptually-motivated frequency scaling, and perfect reconstruction capabilities.

Contribution

The paper presents ISAC, a new filter bank with invertibility, stability, and customizability, enabling effective ML integration and perceptually-motivated audio analysis.

Findings

Supports perfect reconstruction between analysis and synthesis

Allows user-defined temporal support and learnable kernels

Aligns with auditory frequency scales for perceptual relevance

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.