Segment-level Metric Learning for Few-shot Bioacoustic Event Detection

2022-07-15 · Haohe Liu, Xubo Liu, Xinhao Mei, Qiuqiang Kong, Wenwu Wang, Mark D. Plumbley

Few-shot bioacoustic event detection is a task that detects the occurrence time of a novel sound given a few examples. Previous methods employ metric learning to build a latent space with the labeled part of different sound classes, also known as positive events. In this study, we propose a segment-level few-shot learning framework that utilizes both the positive and negative events during model optimization. Training with negative events, which are larger in volume than positive events, can increase the generalization ability of the model. In addition, we use transductive inference on the validation set during training for better adaptation to novel classes. We conduct ablation studies on our proposed method with different setups on input features, training data, and hyper-parameters. Our final system achieves an F-measure of 62.73 on the DCASE 2022 challenge task 5 (DCASE2022-T5) validation set, outperforming the performance of the baseline prototypical network 34.02 by a large margin. Using the proposed method, our submitted system ranks 2nd in DCASE2022-T5. The code of this paper is fully open-sourced at https://github.com/haoheliu/DCASE_2022_Task_5.

📄 PDF Abstract BibTeX arXiv:2207.07773

Code (1)

haoheliu/dcase_2022_task_5 공식 구현 pytorch

Tasks

Event DetectionFew-Shot Learning Metric LearningModel Optimization

Methods 이 논문이 사용한 방법론

Transductive Inference 설명 없음

Multitask frame-level learning for few-shot sound event detection

2024-03-17 · Liang Zou, Genwei Yan, Ruoyu Wang, Jun Du 외

This paper focuses on few-shot Sound Event Detection (SED), which aims to automatically recognize and classify sound events with limited samples. However, prevailing methods methods in few-shot SED predominantly rely on …

Data Augmentation Event Detection Sound Event Detection

Synthetic data enables context-aware bioacoustic sound event detection

2025-03-01 · Benjamin Hoffman, David Robinson, Marius Miron, Vittorio Baglione 외

We propose a methodology for training foundation models that enhances their in-context learning capabilities within the domain of bioacoustic signal processing. We use synthetically generated training data, introducing a…

Event Detection In-Context Learning Sound Event Detection

Pretraining Representations for Bioacoustic Few-shot Detection using Supervised Contrastive Learning

2023-09-02 · Ilyass Moummad, Romain Serizel, Nicolas Farrugia

Deep learning has been widely used recently for sound event detection and classification. Its success is linked to the availability of sufficiently large datasets, possibly with corresponding annotations when supervised …

Contrastive Learning Data Augmentation Event Detection Few-Shot Learning+1

Few-shot bioacoustic event detection at the DCASE 2022 challenge

2022-07-14 · I. Nolasco, S. Singh, E. Vidana-Villa, E. Grout 외

Few-shot sound event detection is the task of detecting sound events, despite having only a few labelled examples of the class of interest. This framework is particularly useful in bioacoustics, where often there is a ne…

Event Detection Sound Event Detection Transductive Learning

Bioacoustic Event Detection with prototypical networks and data augmentation

2021-12-16 · Mark Anderson, Naomi Harte

This report presents deep learning and data augmentation techniques used by a system entered into the Few-Shot Bioacoustic Event Detection for the DCASE2021 Challenge. The remit was to develop a few-shot learning system …

Data Augmentation Event Detection Few-Shot Learning