在微控制器上实现超轻量级鸟类音频检测，显著减少误触发并延长监测时间。
Ultra-Compact CNN Architectures for Tropical Bird Audio Detection on Microcontrollers
- 设计三款极小化的INT8量化卷积神经网络，适配低内存设备
- 在东南亚热带数据集上达到98.3%平均召回率，比传统方法多捕获8个百分点的鸣叫声
- 可直接替换现有设备中的粗略触发器，适合生态监测与边缘计算场景
热带生物多样性被动声学监测受限于持续录音带来的存储与功耗成本，其中鸟类鸣叫通常仅占音频的10%以下。基于低功耗微控制器（如ARM Cortex-M，≤256 kB RAM）的自主记录设备通过仅在可能为正样本的片段触发来缓解此问题，但现有方案效果不佳：如Goertzel滤波器等粗粒度频域能量触发器在约71%精度下产生大量误报；而专为温带单物种任务设计的神经网络模型要么过大无法部署，要么迁移到物种丰富的热带环境时表现差。本文提出DrongoNet系列三种INT8量化卷积神经网络，专为该资源受限环境设计，并在包含5万段音频、1,677个物种的东南亚热带数据集SEABAD上验证。主打模型DrongoNet-Micro（919参数，6.26 kB，0.9810 AUC，τ=0.35时均值召回率98.3%），可直接替代商用野外记录器中的Goertzel触发器：在α=0.10的热带出现率下，比Goertzel多捕获8个百分点的鸟鸣，使32 GB存储卡的监测时长从约28天延长至约45天。DrongoNet-Nano（5.09 kB）面向超低闪存场景；DrongoNet-Edge（33.06 kB，0.9991 AUC）面向Linux SBC。在SEABAD上，Micro模型以28倍更少参数实现与重训练后的TinyChirp CNN-Mel基线相当的0.1 pp AUC性能，证实该系列对梅尔频谱鸟鸣数据集具有部署无关性，但需针对具体环境重新训练。全部三款模型经全INT8量化后，性能损失小于0.12% AUC。
原文摘要 · Abstract (English)
Passive acoustic monitoring of tropical biodiversity is bottlenecked by the storage and battery cost of continuously recording soundscapes in which bird vocalisations typically occupy less than 10% of the audio. Autonomous recording units built on low-power microcontrollers (typically ARM Cortex-M with $\leq$256 kB of RAM) address this by triggering only on likely-positive segments, but the on-device options are unsatisfying: coarse frequency-energy triggers such as Goertzel filters flood SD cards with false positives at $\sim$71% precision, whereas neural detectors developed for temperate single-species tasks are either too large to deploy or transfer poorly to species-rich tropical settings. We present DrongoNet, a family of three INT8 CNN detectors sized for this envelope and validated on a 50,000-clip, 1,677-species Southeast Asian tropical dataset (SEABAD). The headline model, DrongoNet-Micro (919 parameters, 6.26 kB, 0.9810 AUC, 98.3\% mean recall at τ = 0.35), is a drop-in replacement for the Goertzel trigger used in commodity field recorders: at α = 0.10 tropical prevalence it captures 8 pp more bird vocalisations than Goertzel and extends a 32 GB card from $\sim$28 to $\sim$45 days of monitoring. DrongoNet-Nano (5.09 kB) bounds the ultra-low-flash extreme; DrongoNet-Edge (33.06 kB, 0.9991 AUC) targets Linux SBCs. On SEABAD, Micro matches a retrained TinyChirp CNN-Mel baseline within 0.1 pp AUC at 28$\times$ fewer parameters, confirming that the family is deployment-agnostic across mel-spectrogram bird corpora but requires per-environment retraining. Full INT8 quantisation costs $<$0.12% AUC across all three variants.
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。