# Receptive Field Regularization Techniques for Audio Classification and Tagging with Deep Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2105.12395 · HTML: https://mlsanity.com/paper/2105.12395/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 62 references that are in the map.
- First posted on arXiv 26 May 2021.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [Deep Double Descent: Where Bigger Models and More Data Hurt](https://mlsanity.com/paper/1912.02292/) (2019)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [FMA: A Dataset For Music Analysis](https://mlsanity.com/paper/1612.01840/) (2016)
- [A multi-device dataset for urban acoustic scene classification](https://mlsanity.com/paper/1807.09840/) (2018)
- [The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene Classification](https://mlsanity.com/paper/1907.01803/) (2019)
- [Audio tagging with noisy labels and minimal supervision](https://mlsanity.com/paper/1906.02975/) (2019)
- [An Attention Mechanism for Musical Instrument Recognition](https://mlsanity.com/paper/1907.04294/) (2019)
- [Integrating the Data Augmentation Scheme with Various Classifiers for Acoustic Scene Modeling](https://mlsanity.com/paper/1907.06639/) (2019)
- [Extended playing techniques: The next milestone in musical instrument recognition](https://mlsanity.com/paper/1808.09730/) (2018)
- [Receptive-field-regularized CNN variants for acoustic scene classification](https://mlsanity.com/paper/1909.02859/) (2019)
- [Emotion and Theme Recognition in Music with Frequency-Aware RF-Regularized CNNs](https://mlsanity.com/paper/1911.05833/) (2019)
- [Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene Classification](https://mlsanity.com/paper/1909.02869/) (2019)
- [Music theme recognition using CNN and self-attention](https://mlsanity.com/paper/1911.07041/) (2019)
- [Learning Multi-instrument Classification with Partial Labels](https://mlsanity.com/paper/2001.08864/) (2020)

## Built on by (most cited first, 17 of 17)

- [Efficient Training of Audio Transformers with Patchout](https://mlsanity.com/paper/2110.05069/) (2021)
- [Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation](https://mlsanity.com/paper/2211.04772/) (2022)
- [Dehazing Ultrasound using Diffusion Models](https://mlsanity.com/paper/2307.11204/) (2023)
- [Device-Robust Acoustic Scene Classification via Impulse Response Augmentation](https://mlsanity.com/paper/2305.07499/) (2023)
- [Audio Embeddings as Teachers for Music Classification](https://mlsanity.com/paper/2306.17424/) (2023)
- [Learning General Audio Representations with Large-Scale Training of Patchout Audio Transformers](https://mlsanity.com/paper/2211.13956/) (2022)
- [Receptive Field Refinement for Convolutional Neural Networks Reliably Improves Predictive Performance](https://mlsanity.com/paper/2211.14487/) (2022)
- [MMViT: Multiscale Multiview Vision Transformers](https://mlsanity.com/paper/2305.00104/) (2023)
- [Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models](https://mlsanity.com/paper/2310.15648/) (2023)
- [Sound Event Classification in an Industrial Environment: Pipe Leakage Detection Use Case](https://mlsanity.com/paper/2205.02706/) (2022)
- [Optimizing Neural Network Scale for ECG Classification](https://mlsanity.com/paper/2308.12492/) (2023)
- [Over-Parameterization and Generalization in Audio Classification](https://mlsanity.com/paper/2107.08933/) (2021)
- [Object-Size-Driven Design of Convolutional Neural Networks: Virtual Axle Detection based on Raw Data](https://mlsanity.com/paper/2309.01574/) (2023)
- [Enhancing the analysis of murine neonatal ultrasonic vocalizations: Development, evaluation, and application of different mathematical models](https://mlsanity.com/paper/2405.12957/) (2024)
- [Improving Acoustic Scene Classification with City Features](https://mlsanity.com/paper/2503.16862/) (2025)
- [SincDPNet: Interpretable Raw-Waveform Bathroom Activity Recognition for Assistive Living](https://mlsanity.com/paper/2609.34907/) (2026)
- [Learning from imperfect teachers for low-resource acoustic generalization](https://mlsanity.com/paper/2610.05256/) (2026)

## Abstract (arXiv)

In this paper, we study the performance of variants of well-known Convolutional Neural Network (CNN) architectures on different audio tasks. We show that tuning the Receptive Field (RF) of CNNs is crucial to their generalization. An insufficient RF limits the CNN's ability to fit the training data. In contrast, CNNs with an excessive RF tend to over-fit the training data and fail to generalize to unseen testing data. As state-of-the-art CNN architectures-in computer vision and other domains-tend to go deeper in terms of number of layers, their RF size increases and therefore they degrade in performance in several audio classification and tagging tasks. We study well-known CNN architectures and how their building blocks affect their receptive field. We propose several systematic approaches to control the RF of CNNs and systematically test the resulting architectures on different audio classification and tagging tasks and datasets. The experiments show that regularizing the RF of CNNs using our proposed approaches can drastically improve the generalization of models, out-performing complex architectures and pre-trained models on larger datasets. The proposed CNNs achieve state-of-the-art results in multiple tasks, from acoustic scene classification to emotion and theme detection in music to instrument recognition, as demonstrated by top ranks in several pertinent challenges (DCASE, MediaEval).