# Toward end-to-end interpretable convolutional neural networks for waveform signals

arXiv: https://arxiv.org/abs/2405.01815 · HTML: https://mlsanity.com/paper/2405.01815/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 20 references that are in the map.
- First posted on arXiv 3 May 2024.

## Builds on (most cited first, 6 of 6)

- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [TorchAudio: Building Blocks for Audio and Speech Processing](https://mlsanity.com/paper/2110.15018/) (2021)
- [Interpretable Convolutional Filters with SincNet](https://mlsanity.com/paper/1811.09725/) (2018)
- [Natural-Logarithm-Rectified Activation Function in Convolutional Neural Networks](https://mlsanity.com/paper/1908.03682/) (2019)
- [A differentiable short-time Fourier transform with respect to the window length](https://mlsanity.com/paper/2208.10886/) (2022)
- [Optimization of data-driven filterbank for automatic speaker verification](https://mlsanity.com/paper/2007.10729/) (2020)

## Built on by (most cited first, 1 of 1)

- [Structural Bottlenecks on Frequency Representation in End-to-End Audio Models](https://mlsanity.com/paper/2607.08545/) (2026)

## Abstract (arXiv)

This paper introduces a novel convolutional neural networks (CNN) framework tailored for end-to-end audio deep learning models, presenting advancements in efficiency and explainability. By benchmarking experiments on three standard speech emotion recognition datasets with five-fold cross-validation, our framework outperforms Mel spectrogram features by up to seven percent. It can potentially replace the Mel-Frequency Cepstral Coefficients (MFCC) while remaining lightweight. Furthermore, we demonstrate the efficiency and interpretability of the front-end layer using the PhysioNet Heart Sound Database, illustrating its ability to handle and capture intricate long waveform patterns. Our contributions offer a portable solution for building efficient and interpretable models for raw waveform data.