Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.21280 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911433280716800 |
|---|---|
| author | Geldenhuys, Christiaan M. Tonitz, Günther Niesler, Thomas R. |
| author_facet | Geldenhuys, Christiaan M. Tonitz, Günther Niesler, Thomas R. |
| contents | While recent sound event detection (SED) systems can identify baleen whale calls in marine audio, challenges related to false positive and minority-class detection persist. We propose the boundary proposal network (BPN), which extends an existing lightweight SED system. The BPN is inspired by work in image object detection and aims to reduce the number of false positive detections. It achieves this by using intermediate latent representations computed within the backbone classification model to gate the final output. When added to an existing SED system, the BPN achieves a 16.8 % absolute increase in precision, as well as 21.3 % and 9.4 % improvements in the F1-score for minority-class d-calls and bp-calls, respectively. We further consider two approaches to the selection of post-processing hyperparameters: a forward-search and a backward-search. By separately optimising event-level and frame-level hyperparameters, these two approaches lead to considerable performance improvements over parameters selected using empirical methods. The complete WhaleVAD-BPN system achieves a cross-validated development F1-score of 0.475, which is a 9.8 % absolute improvement over the baseline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_21280 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WhaleVAD-BPN: Improving Baleen Whale Call Detection with Boundary Proposal Networks and Post-processing Optimisation Geldenhuys, Christiaan M. Tonitz, Günther Niesler, Thomas R. Audio and Speech Processing Artificial Intelligence Machine Learning Sound Quantitative Methods While recent sound event detection (SED) systems can identify baleen whale calls in marine audio, challenges related to false positive and minority-class detection persist. We propose the boundary proposal network (BPN), which extends an existing lightweight SED system. The BPN is inspired by work in image object detection and aims to reduce the number of false positive detections. It achieves this by using intermediate latent representations computed within the backbone classification model to gate the final output. When added to an existing SED system, the BPN achieves a 16.8 % absolute increase in precision, as well as 21.3 % and 9.4 % improvements in the F1-score for minority-class d-calls and bp-calls, respectively. We further consider two approaches to the selection of post-processing hyperparameters: a forward-search and a backward-search. By separately optimising event-level and frame-level hyperparameters, these two approaches lead to considerable performance improvements over parameters selected using empirical methods. The complete WhaleVAD-BPN system achieves a cross-validated development F1-score of 0.475, which is a 9.8 % absolute improvement over the baseline. |
| title | WhaleVAD-BPN: Improving Baleen Whale Call Detection with Boundary Proposal Networks and Post-processing Optimisation |
| topic | Audio and Speech Processing Artificial Intelligence Machine Learning Sound Quantitative Methods |
| url | https://arxiv.org/abs/2510.21280 |