Effective Pre-Training of Audio Transformers for Sound Event Detection
Florian Schmid, Tobias Morocutti, Francesco Foscarin, Jan Schlüter, Paul Primus, Gerhard Widmer
Abstract
We propose a pre-training pipeline for audio spectrogram transformers for frame-level sound event detection tasks. On top of common pre-training steps, we add a meticulously designed training routine on AudioSet frame-level annotations. This includes a balanced sampler, aggressive data augmentation, and ensemble knowledge distillation. For five transformers, we obtain a substantial performance improvement over previously available checkpoints both on AudioSet frame-level predictions and on frame-level sound event detection downstream tasks, confirming our pipeline’s effectiveness. We publish the resulting checkpoints that researchers can directly fine-tune to build high-performance models for sound event detection tasks.
BibTeX
@inproceedings{icassp2025_effectivepretrai,
title = {Effective Pre-Training of Audio Transformers for Sound Event Detection},
author = {Florian Schmid and Tobias Morocutti and Francesco Foscarin and Jan Schlüter and Paul Primus and Gerhard Widmer},
booktitle = {ICASSP 2025},
year = {2025}
}