mlsanityData to 14 Oct 2026

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

arXiv 2505.07709 ↗First posted 12 May 2025cs.SD cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 33 references that are in the map. First posted on arXiv 12 May 2025.

Builds on

16 of 33 references.

References · 16

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  2. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  3. 2018Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separationcited by 406
  4. 2017Parseval Networks: Improving Robustness to Adversarial Examplescited by 293
  5. 2018Speaker Recognition from Raw Waveform with SincNetcited by 166
  6. 2021LEAF: A Learnable Frontend for Audio Classificationcited by 69
  7. 2017Learning Filterbanks from Raw Speech for Phone Recognitioncited by 25
  8. 2020Data augmentation and loss normalization for deep noise suppressioncited by 23
  9. 2021Spectral Leakage and Rethinking the Kernel Size in CNNscited by 11
  10. 2021FastAudio: A Learnable Audio Front-End for Spoof Speech Detectioncited by 8
  11. 2017Kapre: On-GPU Audio Preprocessing Layers for a Quick Implementation of Deep Neural Network Models with Kerascited by 6
  12. 2017DNN Filter Bank Cepstral Coefficients for Spoofing Detectioncited by 5
4 more
  1. 2024(Almost) Smooth Sailing: Towards Numerical Stability of Neural Networks Through Differentiable Regularization of the Condition Numbercited by 5
  2. 2023Instabilities in Convnets for Raw Audiocited by 2
  3. 2024Hold Me Tight: Stable Encoder-Decoder Design for Speech Enhancementcited by 2
  4. 2014Designing Gabor windows using convex optimizationcited by 1

Built on by

Not cited yet.