In this study, we evaluate the efficacy of the Mamba architecture bioacoustics by introducing BioMamba, a Mamba-based audio representation model for wildlife sounds. We pre-train a BioMamba using self-supervised learning on a large audio corpus and evaluate it on the BEANS benchmark across diverse classification and detection tasks. Compared to the state-of-the-art Transformer-based model (AVES), BioMamba achieves comparable performance while significantly reducing VRAM consumption. Our results demonstrate Mamba's potential as a computationally efficient alternative for real-world environmental monitoring.
animal2vec and MeerKAT: A self-supervised transformer for rare-event raw audio input and a large-scale reference dataset for bioacoustics
Department for the Ecology of Animal Societies, Max Planck Institute of Animal Behavior(动物社会生态学部,动物行为马克斯·普朗克研究所);Department of Biology, University of Konstanz(康斯坦茨大学生物系);Centre for the Advanced Study of Collective Behaviour, University of Konstanz(集体行为高级研究所以及康斯坦茨大学);Kalahari Research Centre, Van Zylsrus, Northern Cape, South Africa(卡拉哈里研究中心,南非北开普省范·齐尔鲁斯);Royal Botanic Gardens Kew, Richmond, UK(皇家植物园肯特,英国里士满);Zukunftskolleg, University of Konstanz(未来学院,康斯坦茨大学);Department of Evolutionary Biology and Environmental Studies, University of Zurich(进化生物学与环境研究部,苏黎世大学);Department of Cognitive Science and Artificial Intelligence, Tilburg University(认知科学与人工智能系,蒂尔堡大学);Naturalis Biodiversity Center, Leiden, The Netherlands(自然史博物馆生物多样性研究中心,莱顿,荷兰);Interdisciplinary Center for the Evolution of Language, University of Zurich(语言进化跨学科研究中心,苏黎世大学);Department of Computer Science, San Diego State University(计算机科学系,圣地亚哥州立大学)
Western Mediterranean wetlands bird species classification: evaluating small-footprint deep learning approaches on a new annotated dataset
La Salle-Universitat Ramon Llull(拉蒙·柳利大学拉萨尔学院)
部署一个运行在无线声学传感器网络上的专家系统,该网络由生物声学监测设备组成,可以从声音中识别鸟类,这将使许多具有生态价值的任务实现自动化,包括分析鸟类种群组成或检测环境利益领域的濒危物种。得益于人工智能的最新进展,赋予这些设备准确的音频分类功能是可能的,其中深度学习技术表现出色。然而,使生物声学设备负担得起的一个关键问题是使用可以嵌入在资源和电池受限的硬件平台中的小足迹深度神经网络。出于这个原因,这项工作提出了两个重型和大型足迹深度神经网络(VGG 16和ResNet 50)和轻量级替代方案MobileNetV2之间的关键比较分析。我们的实验结果表明,MobileNetV2的平均F1分数比ResNet50低不到5%(0.789 vs. 0.834),表现优于VGG16,占用空间小近40倍。此外,为了比较模型,我们创建并公开了西地中海湿地鸟类数据集,包括201.6分钟和5,795个Aiguamolls de l'Empordà自然公园20种特有鸟类的音频摘录。
Deep learning for music generation. Four approaches and their comparative evaluation
Faculty of Automatics and Computer Science, University POLITEHNICA of Bucharest(布加勒斯特理工大学自动控制与计算机科学学院);Romanian Academy Research Institute for Artificial Intelligence(罗马尼亚科学院人工智能研究所);Academy of Romanian Scientists(罗马尼亚科学院)
Generalization in birdsong classification: impact of transfer learning methods and dataset characteristics
Naturalis Biodiversity Center(自然生物多样性中心);Xeno-Canto Foundation(异音基金会);Landesbund fur Vogel- und Naturschutz(鸟类与自然保护州联合会);Department of Cognitive Science and Artificial Intelligence, Tilburg University(蒂尔堡大学认知科学与人工智能系)
Comparative Analysis of CNN and Transformer Architectures with Heart Cycle Normalization for Automated Phonocardiogram Classification
Fraunhofer Institute for Software and Systems Engineering ISST(弗劳恩霍夫软件与系统工程研究所);Department of Computer Science, University of Applied Sciences and Arts Dortmund(应用科学大学多特蒙德计算机科学系);Department of Computer Science, TU Dortmund University(图尔努恩大学计算机科学系);Department of Health Informatics, School of Medicine, Witten/Herdecke University(医学学院健康信息学系,维滕/赫尔德克大学);Institute for Medical Informatics, Biometry and Epidemiology (IMIBE), University Hospital Essen(医学信息学、生物统计与流行病学研究所(IMIBE),埃森大学医院)