arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.09970eess.AScs.SD
收藏

BioME:一种适用于物联网应用的资源高效生物声学基础模型

BioME: A Resource-Efficient Bioacoustic Foundational Model for IoT Applications

Institut national de la recherche scientifique (INRS - EMT)(加拿大国家科学研究机构(INRS - EMT))

Heitor R. Guimarães, Abhishek Tiwari, Mahsa Abdollahi, Anderson R. Avila, Tiago H. Falk

AI总结:

BioME是一种通过逐层蒸馏实现高效资源利用的生物声学基础模型,适用于物联网应用,通过整合调制感知特征提升生态泛化能力。

摘要:

被动声学监测已成为生物多样性评估、保护和行为生态学中的关键策略,特别是在物联网(IoT)设备能够实现大规模连续现场音频收集的情况下。尽管最近基于自监督学习(SSL)的音频编码器,如BEATs和AVES,在生物声学任务中表现出色,但其计算成本和对未知环境的鲁棒性不足阻碍了在资源受限平台上的部署。在本工作中,我们引入了BioME,一种专为生物声学应用设计的资源高效音频编码器。BioME通过逐层蒸馏从高容量教师模型进行训练,从而在减少参数数量75%的同时实现强大的表征迁移能力。为进一步提高生态泛化能力,该模型在涵盖语音、环境声音和动物叫声的多领域数据上进行预训练。关键贡献是通过FiLM条件化整合调制感知的声学特征,注入了受数字信号处理(DSP)启发的归纳偏差,从而在低容量范围内增强特征解耦能力。在多个生物声学任务中,BioME的表现与更大模型相当或优于其教师模型,同时适用于资源受限的物联网部署。为了可复现性,代码和预训练检查点已公开可用。

英文摘要:

Passive acoustic monitoring has become a key strategy in biodiversity assessment, conservation, and behavioral ecology, especially as Internet-of-Things (IoT) devices enable continuous in situ audio collection at scale. While recent self-supervised learning (SSL)-based audio encoders, such as BEATs and AVES, have shown strong performance in bioacoustic tasks, their computational cost and limited robustness to unseen environments hinder deployment on resource-constrained platforms. In this work, we introduce BioME, a resource-efficient audio encoder designed for bioacoustic applications. BioME is trained via layer-to-layer distillation from a high-capacity teacher model, enabling strong representational transfer while reducing the parameter count by 75%. To further improve ecological generalization, the model is pretrained on multi-domain data spanning speech, environmental sounds, and animal vocalizations. A key contribution is the integration of modulation-aware acoustic features via FiLM conditioning, injecting a DSP-inspired inductive bias that enhances feature disentanglement in low-capacity regimes. Across multiple bioacoustic tasks, BioME matches or surpasses the performance of larger models, including its teacher, while being suitable for resource-constrained IoT deployments. For reproducibility, code and pretrained checkpoints are publicly available.

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。

↑