arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.12082cs.SDcs.LGeess.ASq-bio.QM
收藏

学习隆隆声:使用深度架构的自动大象叫声分类、检测与端点检测

Learning to rumble: Automated elephant call classification, detection and endpointing using deep architectures

University of Stellenbosch(斯泰伦博斯大学)

Christiaan M. Geldenhuys, Thomas R. Niesler

AI总结:

本研究提出在帧级别检测大象叫声并使用音频频谱图变换器(AST)进行分类与端点检测,在多个数据集上取得了优于现有系统的性能,证明了全自动大象叫声检测与子叫声分类系统的可行性。

摘要:

我们考虑在连续录音中检测、分离和分类大象叫声的问题。这种自动叫声特征化可以协助保护工作并为环境管理策略提供信息。与以往在片段级别进行叫声检测的工作不同,我们在帧级别进行叫声检测,这也隐含地允许叫声端点检测,即在较长的录音中分离出叫声。在实验中,我们使用了两个带注释的数据集,一个包含亚洲象的声音,另一个包含非洲象的声音。我们评估了几个浅层和深层分类器模型,并表明通过使用音频频谱图变换器(AST,一种以前未用于此目的的神经网络架构,我们已将其配置为新颖的序列到序列方式),可以改善当前的最佳性能。我们还表明,通过预训练使用迁移学习可以在计算复杂度和性能方面带来进一步的改进。最后,我们考虑使用公认的叫声类型分类法进行子叫声分类,这是一项以前未被考虑的任务。我们表明,在这种情况下,变换器架构也能提供最佳性能。我们最好的分类器在帧级二元叫声分类中实现了0.962的平均精度(AP),在5类叫声分类和7类子叫声分类中分别实现了0.957和0.979的受试者工作特征曲线下面积(AUC)。所有这些结果都代表了新的基准(子叫声分类)或对先前最佳系统的改进。我们得出结论,全自动大象叫声检测和子叫声分类系统已触手可及。这样的系统将为保护和管理目的提供有关象群行为和状态的宝贵信息。

英文摘要:

We consider the problem of detecting, isolating and classifying elephant calls in continuously recorded audio. Such automatic call characterisation can assist conservation efforts and inform environmental management strategies. In contrast to previous work in which call detection was performed at a segment level, we perform call detection at a frame level which implicitly also allows call endpointing, the isolation of a call in a longer recording. For experimentation, we employ two annotated datasets, one containing Asian and the other African elephant vocalisations. We evaluate several shallow and deep classifier models, and show that the current best performance can be improved by using an audio spectrogram transformer (AST), a neural architecture which has not been used for this purpose before, and which we have configured in a novel sequence-to-sequence manner. We also show that using transfer learning by pre-training leads to further improvements both in terms of computational complexity and performance. Finally, we consider sub-call classification using an accepted taxonomy of call types, a task which has not previously been considered. We show that also in this case the transformer architectures provide the best performance. Our best classifiers achieve an average precision (AP) of 0.962 for framewise binary call classification, and an area under the receiver operating characteristic (AUC) of 0.957 and 0.979 for call classification with 5 classes and sub-call classification with 7 classes respectively. All of these represent either new benchmarks (sub-call classifications) or improvements on previously best systems. We conclude that a fully-automated elephant call detection and subcall classification system is within reach. Such a system would provide valuable information on the behaviour and state of elephant herds for the purposes of conservation and management.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑