用半监督多任务学习提升蝗虫鸣声识别，效果远超通用模型。
Decoding Insect Song: A Multitask Semisupervised Orthoptera Bioacoustic Classifier
- 融合弱监督分类与自监督学习，从无标签音频中提取特征。
- 在多个指标上超越顶尖通用模型，主动学习后F1达0.34。
- 生成的嵌入可揭示生态结构，适合生态学家探索物种分布。
被动声学监测在生态推断中潜力巨大，但现有自动化工具通常训练范围狭窄且难以迁移。我们提出PULSE框架，一种针对直翅目昆虫生物声学的半监督多任务方法，结合弱监督物种分类、对未标注野外音频的自监督学习，以及从通用生物声学模型中蒸馏知识。领域适配的专业模型在所有指标上均优于最先进的通用模型（宏F1：0.21 vs. 0.07；AUC：0.74 vs. 0.45；AP：0.32 vs. 0.19），主动学习进一步将F1提升至0.34，AUC达0.84。除分类外，所学嵌入编码了生态上有意义的结构，通过交互式可视化工具支持生态发现。
原文摘要 · Abstract (English)
Passive acoustic monitoring holds great promise for ecological inference, yet existing automated tools are typically narrowly trained and non-transferable. We address these limitations with PULSE, a semi-supervised, multi-task framework for Orthoptera bioacoustics, combining weakly-supervised species classification, self-supervised learning on unlabelled field audio, and knowledge distillation from a general-purpose bioacoustic model. Our domain-adapted specialist model outperforms a state-of-the-art general model across all metrics (macro F1: 0.21 vs. 0.07; AUC: 0.74 vs. 0.45; AP: 0.32 vs. 0.19), with active learning further raising F1 to 0.34 and AUC to 0.84. Beyond classification, the learned embeddings encode ecologically meaningful structure, exposed through an interactive visualisation tool for ecological discovery.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。