# Maximizing Audio Event Detection Model Performance on Small Datasets Through Knowledge Transfer, Data Augmentation, And Pretraining: An Ablation Study

arXiv: https://arxiv.org/abs/2202.03514 · HTML: https://mlsanity.com/paper/2202.03514/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 7 Feb 2022.

## Builds on (most cited first, 13 of 13)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition](https://mlsanity.com/paper/2109.13226/) (2021)
- [Rethinking CNN Models for Audio Classification](https://mlsanity.com/paper/2007.11154/) (2020)
- [Negative Data Augmentation](https://mlsanity.com/paper/2102.05113/) (2021)
- [ESResNet: Environmental Sound Classification Based on Visual Domain Models](https://mlsanity.com/paper/2004.07301/) (2020)
- [Mixup-Based Acoustic Scene Classification Using Multi-Channel Convolutional Neural Network](https://mlsanity.com/paper/1805.07319/) (2018)
- [A Sequential Self Teaching Approach for Improving Generalization in Sound Event Recognition](https://mlsanity.com/paper/2007.00144/) (2020)
- [Deep Convolutional Neural Networks and Data Augmentation for Acoustic Event Detection](https://mlsanity.com/paper/1604.07160/) (2016)
- [Sample Mixed-Based Data Augmentation for Domestic Audio Tagging](https://mlsanity.com/paper/1808.03883/) (2018)

## Abstract (arXiv)

An Xception model reaches state-of-the-art (SOTA) accuracy on the ESC-50 dataset for audio event detection through knowledge transfer from ImageNet weights, pretraining on AudioSet, and an on-the-fly data augmentation pipeline. This paper presents an ablation study that analyzes which components contribute to the boost in performance and training time. A smaller Xception model is also presented which nears SOTA performance with almost a third of the parameters.