# Interpretable Convolutional Filters with SincNet

arXiv: https://arxiv.org/abs/1811.09725 · HTML: https://mlsanity.com/paper/1811.09725/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2018.

## Built on by (most cited first, 20 of 20)

- [BENDR: using transformers and a contrastive self-supervised learning task to learn from massive amounts of EEG data](https://mlsanity.com/paper/2101.12037/) (2021)
- [Deep Riemannian Networks for End-to-End EEG Decoding](https://mlsanity.com/paper/2212.10426/) (2022)
- [Focal Modulation Networks for Interpretable Sound Classification](https://mlsanity.com/paper/2402.02754/) (2024)
- [Interpreting intermediate convolutional layers of generative CNNs trained on waveforms](https://mlsanity.com/paper/2104.09489/) (2021)
- [Learning Temporal Resolution in Spectrogram for Audio Classification](https://mlsanity.com/paper/2210.01719/) (2022)
- [Learning Non-linear Wavelet Transformation via Normalizing Flow](https://mlsanity.com/paper/2101.11306/) (2021)
- [Interpretable SincNet-based Deep Learning for Emotion Recognition from EEG brain activity](https://mlsanity.com/paper/2107.10790/) (2021)
- [Interpreting intermediate convolutional layers in unsupervised acoustic word classification](https://mlsanity.com/paper/2110.02375/) (2021)
- [TFN: An Interpretable Neural Network with Time-Frequency Transform Embedded for Intelligent Fault Diagnosis](https://mlsanity.com/paper/2209.01992/) (2022)
- [Phonological Level wav2vec2-based Mispronunciation Detection and Diagnosis Method](https://mlsanity.com/paper/2311.07037/) (2023)
- [Speech recognition for air traffic control via feature learning and end-to-end training](https://mlsanity.com/paper/2111.02654/) (2021)
- [Tailored Design of Audio-Visual Speech Recognition Models using Branchformers](https://mlsanity.com/paper/2407.06606/) (2024)
- [Echoes of Phonetics: Unveiling Relevant Acoustic Cues for ASR via Feature Attribution](https://mlsanity.com/paper/2506.02181/) (2025)
- [Toward end-to-end interpretable convolutional neural networks for waveform signals](https://mlsanity.com/paper/2405.01815/) (2024)
- [Interpretable Acoustic Representation Learning on Breathing and Speech Signals for COVID-19 Detection](https://mlsanity.com/paper/2206.13365/) (2022)
- [Dynamic Time-Alignment of Dimensional Annotations of Emotion using Recurrent Neural Networks](https://mlsanity.com/paper/2209.10223/) (2022)
- [SincPD: An Explainable Method based on Sinc Filters to Diagnose Parkinson's Disease Severity by Gait Cycle Analysis](https://mlsanity.com/paper/2502.17463/) (2025)
- [Acoustic Classification of Maritime Vessels using Learnable Filterbanks](https://mlsanity.com/paper/2505.23964/) (2025)
- [From Self-Supervised Speech Models to Mixture-of-Experts for Robust Anti-Spoofing](https://mlsanity.com/paper/2606.14639/) (2026)
- [Structural Bottlenecks on Frequency Representation in End-to-End Audio Models](https://mlsanity.com/paper/2607.08545/) (2026)

## Abstract (arXiv)

Deep learning is currently playing a crucial role toward higher levels of artificial intelligence. This paradigm allows neural networks to learn complex and abstract representations, that are progressively obtained by combining simpler ones. Nevertheless, the internal "black-box" representations automatically discovered by current neural architectures often suffer from a lack of interpretability, making of primary interest the study of explainable machine learning techniques. This paper summarizes our recent efforts to develop a more interpretable neural model for directly processing speech from the raw waveform. In particular, we propose SincNet, a novel Convolutional Neural Network (CNN) that encourages the first layer to discover more meaningful filters by exploiting parametrized sinc functions. In contrast to standard CNNs, which learn all the elements of each filter, only low and high cutoff frequencies of band-pass filters are directly learned from data. This inductive bias offers a very compact way to derive a customized filter-bank front-end, that only depends on some parameters with a clear physical meaning. Our experiments, conducted on both speaker and speech recognition, show that the proposed architecture converges faster, performs better, and is more interpretable than standard CNNs.