利用录音元数据提升生物声学模型的泛化能力
MetaPerch: Learning from metadata for bioacoustics foundation models
- 用位置、时间等元数据作为辅助监督信号
- 在17个数据集上实现跨域强性能表现
- 适合需要应对真实环境变化的声学监测场景
生物声学基础模型依赖如Xeno-Canto这样的公民科学平台获取地理和生态多样性丰富的数据。已有研究证明，仅使用标注数据即可训练出顶尖的物种检测模型；然而，这些社区驱动数据平台中丰富的录音元数据仍未被充分利用。本文探索将位置、时间等元数据作为辅助监督信号，使模型学习物种与元数据间的关联，从而在表征中引入额外信息。这种元数据损失有助于构建更丰富、更鲁棒的表示，提升对物种分布和声学域偏移的泛化能力，这对实际被动声学监测（PAM）部署至关重要。我们提出MetaPerch，一个新基础模型，在多个挑战性领域均表现出色，并系统研究了9种不同元数据源对17个生物声学数据集的影响。
原文摘要 · Abstract (English)
Bioacoustic foundation models rely on large-scale citizen science platforms like Xeno-Canto for geographically and ecologically diverse data. Recent work has shown that supervision alone can produce SotA species detection models when trained on this large-scale data -- however, there remains unutilized potential in the form of recording metadata readily available within these community-driven data hubs. In this work, we explore the use of metadata -- such as location and time -- as auxiliary supervision signals, allowing the model to leverage species-metadata correlations in its learned representation. Auxiliary metadata losses provide additional information beyond vocalizations alone that can encourage a richer, more robust representation that generalizes better to species distribution and acoustic domain shifts -- important challenges for deployment in real-world passive acoustic monitoring (PAM) settings. We introduce MetaPerch, a new foundation model that achieves strong species identification performance across multiple challenging domains and present an extensive empirical study of the effects of 9 diverse metadata sources on 17 bioacoustic datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。