# The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene Classification

arXiv: https://arxiv.org/abs/1907.01803 · HTML: https://mlsanity.com/paper/1907.01803/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2019.

## Built on by (most cited first, 22 of 22)

- [Efficient Training of Audio Transformers with Patchout](https://mlsanity.com/paper/2110.05069/) (2021)
- [Slow-Fast Auditory Streams For Audio Recognition](https://mlsanity.com/paper/2103.03516/) (2021)
- [Pixel-Grounded Prototypical Part Networks](https://mlsanity.com/paper/2309.14531/) (2023)
- [Receptive Field Regularization Techniques for Audio Classification and Tagging with Deep Convolutional Neural Networks](https://mlsanity.com/paper/2105.12395/) (2021)
- [SubSpectral Normalization for Neural Audio Data Processing](https://mlsanity.com/paper/2103.13620/) (2021)
- [Device-Robust Acoustic Scene Classification via Impulse Response Augmentation](https://mlsanity.com/paper/2305.07499/) (2023)
- [QTI Submission to DCASE 2021: residual normalization for device-imbalanced acoustic scene classification with efficient design](https://mlsanity.com/paper/2206.13909/) (2022)
- [Understanding the Influence of Receptive Field and Network Complexity in Neural-Network-Guided TEM Image Analysis](https://mlsanity.com/paper/2204.04250/) (2022)
- [IDMT-Traffic: An Open Benchmark Dataset for Acoustic Traffic Monitoring Research](https://mlsanity.com/paper/2104.13620/) (2021)
- [Domain Generalization on Efficient Acoustic Scene Classification using Residual Normalization](https://mlsanity.com/paper/2111.06531/) (2021)
- [Learning General Audio Representations with Large-Scale Training of Patchout Audio Transformers](https://mlsanity.com/paper/2211.13956/) (2022)
- [AI-in-the-Loop -- The impact of HMI in AI-based Application](https://mlsanity.com/paper/2303.11508/) (2023)
- [DESED-FL and URBAN-FL: Federated Learning Datasets for Sound Event Detection](https://mlsanity.com/paper/2102.08833/) (2021)
- [A Case Study of Deep Learning Based Multi-Modal Methods for Predicting the Age-Suitability Rating of Movie Trailers](https://mlsanity.com/paper/2101.11704/) (2021)
- [Towards Explaining Expressive Qualities in Piano Recordings: Transfer of Explanatory Features via Acoustic Domain Adaptation](https://mlsanity.com/paper/2102.13479/) (2021)
- [SVGraph: Learning Semantic Graphs from Instructional Videos](https://mlsanity.com/paper/2207.08001/) (2022)
- [Universal Deoxidation of Semiconductor Substrates Assisted by Machine-Learning and Real-Time-Feedback-Control](https://mlsanity.com/paper/2312.01662/) (2023)
- [Over-Parameterization and Generalization in Audio Classification](https://mlsanity.com/paper/2107.08933/) (2021)
- [Metric-based multimodal meta-learning for human movement identification via footstep recognition](https://mlsanity.com/paper/2111.07979/) (2021)
- [Enhancing Small Object Encoding in Deep Neural Networks: Introducing Fast&Focused-Net with Volume-wise Dot Product Layer](https://mlsanity.com/paper/2401.09823/) (2024)
- [Improving Acoustic Scene Classification with City Features](https://mlsanity.com/paper/2503.16862/) (2025)
- [Local Information Matters: A Rethink of Crowd Counting](https://mlsanity.com/paper/2508.16970/) (2025)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) have had great success in many machine vision as well as machine audition tasks. Many image recognition network architectures have consequently been adapted for audio processing tasks. However, despite some successes, the performance of many of these did not translate from the image to the audio domain. For example, very deep architectures such as ResNet and DenseNet, which significantly outperform VGG in image recognition, do not perform better in audio processing tasks such as Acoustic Scene Classification (ASC). In this paper, we investigate the reasons why such powerful architectures perform worse in ASC compared to simpler models (e.g., VGG). To this end, we analyse the receptive field (RF) of these CNNs and demonstrate the importance of the RF to the generalization capability of the models. Using our receptive field analysis, we adapt both ResNet and DenseNet, achieving state-of-the-art performance and eventually outperforming the VGG-based models. We introduce systematic ways of adapting the RF in CNNs, and present results on three data sets that show how changing the RF over the time and frequency dimensions affects a model's performance. Our experimental results show that very small or very large RFs can cause performance degradation, but deep models can be made to generalize well by carefully choosing an appropriate RF size within a certain range.