# Sound Event Bounding Boxes

arXiv: https://arxiv.org/abs/2406.04212 · HTML: https://mlsanity.com/paper/2406.04212/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2024.

## Built on by (most cited first, 7 of 7)

- [Robust detection of overlapping bioacoustic sound events](https://mlsanity.com/paper/2503.02389/) (2025)
- [Prototype based Masked Audio Model for Self-Supervised Learning of Sound Event Detection](https://mlsanity.com/paper/2409.17656/) (2024)
- [RealDESED: A Real-World Domestic Sound Event Detection Benchmark](https://mlsanity.com/paper/2607.16736/) (2026)
- [Boundary Regression for Leitmotif Detection in Music Audio](https://mlsanity.com/paper/2503.07977/) (2025)
- [Revisiting SSL for sound event detection: complementary fusion and adaptive post-processing](https://mlsanity.com/paper/2505.11889/) (2025)
- [Semi-Supervised Sound Event Detection with Conditional Mixup and Embedding-Level Contrastive Loss](https://mlsanity.com/paper/2606.29901/) (2026)
- [MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-Training](https://mlsanity.com/paper/2609.15221/) (2026)

## Abstract (arXiv)

Sound event detection is the task of recognizing sounds and determining their extent (onset/offset times) within an audio clip. Existing systems commonly predict sound presence confidence in short time frames. Then, thresholding produces binary frame-level presence decisions, with the extent of individual events determined by merging consecutive positive frames. In this paper, we show that frame-level thresholding degrades the prediction of the event extent by coupling it with the system's sound presence confidence. We propose to decouple the prediction of event extent and confidence by introducing SEBBs, which format each sound event prediction as a tuple of a class type, extent, and overall confidence. We also propose a change-detection-based algorithm to convert legacy frame-level outputs into SEBBs. We find the algorithm significantly improves the performance of DCASE 2023 Challenge systems, boosting the state of the art from .644 to .686 PSDS1.