ChiroEcho: extending automated bat vocalisation classification beyond the learned taxonomy
ChiroEcho: extending automated bat vocalisation classification beyond the learned taxonomy
ChiroEcho：将自动蝙蝠发声分类扩展至已学习分类法之外
Bats are key indicators of ecosystem health and are protected throughout Europe, making reliable population monitoring a conservation priority. Their cryptic nocturnal lifestyle makes passive acoustic monitoring essential, yet automated identification remains difficult as echolocation calls vary with behaviour and environment and overlap among species.
蝙蝠是生态系统健康的关键指标，在欧洲受到全面保护，因此可靠的种群监测成为保护工作的重中之重。由于蝙蝠具有隐秘的夜行习性，被动声学监测至关重要；然而，自动识别仍然面临挑战，因为回声定位叫声会随行为和环境而变化，且不同物种间的叫声存在重叠。
We present a deep learning framework that jointly predicts species and genus and combines genus predictions with geographic species distributions at inference. When only one species of a predicted genus occurs in a region, the framework can resolve species absent from the learned taxonomy. This reframes geographic information as a means of extending, rather than constraining, a classifier’s effective taxonomy.
我们提出了一个深度学习框架，该框架能够联合预测物种和属，并在推理阶段将属的预测结果与地理物种分布相结合。当某个地区仅存在预测属中的一个物种时，该框架能够识别出那些未包含在已学习分类法中的物种。这重新定义了地理信息的作用，将其作为扩展而非限制分类器有效分类法的一种手段。
Using recordings spanning 35 European bat species, we evaluate closed-set classification, examine the instability of performance estimates for sparsely represented species, and conduct a controlled held-out proof-of-principle experiment. The rare-species analysis shows how limited evaluation data can obscure species-level performance, while the held-out experiment shows that genus predictions and location can recover labels unavailable to the species head.
通过使用涵盖 35 种欧洲蝙蝠的录音，我们评估了封闭集分类，检查了稀有物种性能估计的不稳定性，并进行了一项受控的留出法原理验证实验。针对稀有物种的分析表明，有限的评估数据如何掩盖物种层面的性能；而留出法实验则证明，属的预测结果和地理位置信息可以恢复物种分类头（species head）无法识别的标签。
Geographic resolution extends operational coverage from 35 to 41 of the 48 native European bat species, increasing coverage from 73% to 85%. To our knowledge, this is the broadest operational coverage reported for automated European bat classification. More broadly, the bat framework provides proof of principle for resolving unseen fine-grained classes by combining coarse predictions with transparent external constraints.
地理分辨率将操作覆盖范围从 48 种欧洲本土蝙蝠中的 35 种扩展到了 41 种，覆盖率从 73% 提升至 85%。据我们所知，这是目前欧洲蝙蝠自动分类领域报道的最广泛的操作覆盖范围。从更广泛的意义上讲，该蝙蝠分类框架通过结合粗粒度预测与透明的外部约束，为解决未见过的细粒度类别提供了原理验证。