Saved in:
Bibliographic Details
Main Authors: Haider, Daniel, Perfler, Felix, Balazs, Peter, Hollomey, Clara, Holighaus, Nicki
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.07709
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909607814758400
author Haider, Daniel
Perfler, Felix
Balazs, Peter
Hollomey, Clara
Holighaus, Nicki
author_facet Haider, Daniel
Perfler, Felix
Balazs, Peter
Hollomey, Clara
Holighaus, Nicki
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_07709
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ISAC: An Invertible and Stable Auditory Filter Bank with Customizable Kernels for ML Integration
Haider, Daniel
Perfler, Felix
Balazs, Peter
Hollomey, Clara
Holighaus, Nicki
Sound
Machine Learning
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.
title ISAC: An Invertible and Stable Auditory Filter Bank with Customizable Kernels for ML Integration
topic Sound
Machine Learning
url https://arxiv.org/abs/2505.07709