ISAC: An Invertible and Stable Auditory Filter Bank with Customizable Kernels for ML Integration
This work addresses the need for perceptually-motivated audio front-ends in machine learning, though it appears incremental as it builds on existing auditory filter concepts with added invertibility and stability features.
The paper tackles the problem of designing an auditory filter bank for audio processing that is both invertible and stable, and can be integrated into machine learning systems, resulting in a customizable and user-friendly front-end for various applications.
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.