Maximizing Audio Event Detection Model Performance on Small Datasets Through Knowledge Transfer, Data Augmentation, And Pretraining: An Ablation Study
Not on the map. Why?
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 20 references that are in the map. First posted on arXiv 7 Feb 2022.
Builds on
13 of 20 references.
References · 13
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
- 2016CNN Architectures for Large-Scale Audio Classificationcited by 701
- 2021AST: Audio Spectrogram Transformercited by 634
- 2019PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognitioncited by 563
- 2021BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognitioncited by 88
- 2020Rethinking CNN Models for Audio Classificationcited by 48
- 2021Negative Data Augmentationcited by 46
- 2020ESResNet: Environmental Sound Classification Based on Visual Domain Modelscited by 31
- 2018Mixup-Based Acoustic Scene Classification Using Multi-Channel Convolutional Neural Networkcited by 16
- 2020A Sequential Self Teaching Approach for Improving Generalization in Sound Event Recognitioncited by 12
- 2016Deep Convolutional Neural Networks and Data Augmentation for Acoustic Event Detectioncited by 10
1 more
Built on by
Not cited yet.