Automatic detection systems are important in passive acoustic monitoring (PAM) systems, as these record large amounts of audio data which are infeasible for humans to evaluate manually. In this paper we evaluated methods for compensating class imbalance for deep-learning based automatic detection of acoustic chimpanzee calls. The prevalence of chimpanzee calls in natural habitats is very rare, i.e. databases feature a heavy imbalance between background and target calls. Such imbalances can have negative effects on classifier performances. We employed a state-of-the-art detection approach based on convolutional recurrent neural networks (CRNNs). We extended the detection pipeline through various stages for compensating class imbalance. These included (1) spectrogram denoising, (2) alternative loss functions, and (3) resampling. Our key findings are: (1) spectrogram denoising operations significantly improved performance for both target classes, (2) standard binary cross entropy reached the highest performance, and (3) manipulating relative class imbalance through resampling either decreased or maintained performance depending on the target class. Finally, we reached detection performances of 33%F1 for drumming and 5%F1 for vocalization, which is a >7 fold increase compared to previously published results. We conclude that supporting the network to learn decoupling noise conditions from foreground classes is of primary importance for increasing performance.

自动检测系统在被动声学监测 (PAM) 系统中很重要，因为它们会记录大量的音频数据，而这些数据是人类无法手动评估的。在本文中，我们评估了基于深度学习的黑猩猩声学呼叫自动检测补偿类不平衡的方法。黑猩猩在自然栖息地发出叫声的情况非常罕见，即数据库在背景和目标叫声之间存在严重失衡。这种不平衡会对分类器性能产生负面影响。我们采用了基于卷积循环神经网络 (CRNN) 的最先进的检测方法。我们通过各个阶段扩展了检测管道以补偿类别不平衡。这些包括 (1) 频谱图去噪，(2) 替代损失函数，以及 (3) 重采样。我们的主要发现是：(1) 频谱图去噪操作显着提高了两个目标类的性能，(2) 标准二元交叉熵达到了最高性能，以及 (3) 通过重采样来操纵相对类不平衡，根据目标类降低或保持性能。最后，我们达到了 33% 的检测性能F 1 用于击鼓，5% F 1 用于发声，与之前公布的结果相比增加了 7 倍以上。我们得出结论，支持网络从前景类中学习去耦噪声条件对于提高性能至关重要。