Few-Shot Bioacoustic Event Detection with Frame-Level Embedding Learning System

2024/07/14 by PengYuan Zhao, Zhao, PengYuan, ChengWei Lu +3 · 1 citation
Engineering · #Advanced Chemical Sensor Technologies #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2407.10182

openalex publication_date 2024/07/14 · openalex created_date 2024/07/17 · openalex updated_date 2026/07/28

Abstract

This technical report presents our frame-level embedding learning system for the DCASE2024 challenge for few-shot bioacoustic event detection (Task 5).In this work, we used log-mel and PCEN for feature extraction of the input audio, Netmamba Encoder as the information interaction network, and adopted data augmentation strategies to improve the generalizability of the trained model as well as multiple post-processing methods. Our final system achieved an F-measure score of 56.4%, securing the 2nd rank in the few-shot bioacoustic event detection category of the Detection and Classification of Acoustic Scenes and Events Challenge 2024.

Cited by

• WhaleVAD-BPN: Improving Baleen Whale Call Detection with Boundary Proposal Networks and Post-processing Optimisation

Related

• Few-shot bioacoustic event detection at the DCASE 2022 challenge
• Surrey System for DCASE 2022 Task 5: Few-shot Bioacoustic Event Detection with Segment-level Metric Learning
• Few-shot bioacoustic event detection at the DCASE 2023 challenge
• Multitask frame-level learning for few-shot sound event detection
• Pretraining Representations for Bioacoustic Few-shot Detection using Supervised Contrastive Learning