Maximizing Audio Event Detection Model Performance on Small Datasets Through Knowledge Transfer, Data Augmentation, and Pretraining: an Ablation Study

Daniel Tompkins; Kshitiz Kumar; Jian Wu

ICASSP 2022accepted0 citations

Maximizing Audio Event Detection Model Performance on Small Datasets Through Knowledge Transfer, Data Augmentation, and Pretraining: an Ablation Study

Abstract

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.

BibTeX

@inproceedings{icassp2022_maximizingaudioe,
  title = {Maximizing Audio Event Detection Model Performance on Small Datasets Through Knowledge Transfer, Data Augmentation, and Pretraining: an Ablation Study},
  author = {Daniel Tompkins and Kshitiz Kumar and Jian Wu},
  booktitle = {ICASSP 2022},
  year = {2022}
}