[论文解读] BioME: A Resource-Efficient Bioacoustic Foundational Model for IoT Applications

Heitor R. Guimarães, Abhishek Tiwari+3 more|arXiv (Cornell University)|Feb 10, 2026

Animal Vocal Communication and Behavior被引用 0

一句话总结

BioME 是一个资源高效的自监督音频编码器，用于生物声学任务，来自大型教师模型的蒸馏并通过 FiLM 的调制特征增强，以在边缘设备和多样生态任务上实现强性能。

ABSTRACT

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.

研究动机与目标

• 为资源受限的物联网部署推动高效的生物声学表征学习。
• 通过蒸馏大型教师模型同时保持跨领域泛化能力，开发一个小而强大的编码器。
• 通过调制感知特征提升表征的解耦，在低容量机制下改善表征。
• 在 BEANS 生物声学基准和声学蜂巢监测任务中展示 BioME 的有效性。

提出的方法

• 基于补丁的音频编码，使用梅尔谱并采用非重叠的 16x16 补丁。
• 基于变换器的编码器，具有分组查询注意力（GQA）和旋转位置嵌入（RoPE），以降低内存与计算。
• FiLM 调制在每一层注入基于调制谱的上下文（MSAB 特征），使表征偏向生物声学信号。
• 使用 L1 加余弦相似性损失进行层级蒸馏，将 BEATs 作为教师传递给深度相匹配（12 层）的学生，并在层 {3,6,9,12} 进行中间对齐。
• 多领域预训练（语音、环境声音、生物声学记录）以提升生态泛化能力。

Figure 1: Spectrogram (top row) and the modulation spectrum (bottom row) plots, averaged across samples, for three hummingbird species: Anna’s hummingbird ( annhum ), Broad-tailed hummingbird ( brthum ), and Costa’s hummingbird ( coshum ).

实验结果

研究问题

• RQ1 紧凑的学生编码器是否可以通过分层蒸馏达到甚至超过其大型教师在生物声学任务上的性能？
• RQ2 通过 FiLM 引入调制基特征是否能在低容量模型中改善表征的解耦？
• RQ3 架构选择（GQA、RoPE、灵感自 Llama 的组件）如何影响边缘设备的效率与准确性？
• RQ4 在边缘部署与基础部署的对比下，BioME 在 BEANS 基准和蜂巢监测任务上的性能权衡如何？

主要发现

• BioME 6M（Edge）实现了最先进的效率，在 BEANS 任务中以多达 15 倍较少的参数超过基线。
• BioME Small（26M）与 Base（76M）在 BEANS 总分上超过教师 BEATs，体现了有效的蒸馏与归纳偏置。
• 通过 FiLM 的调制特征（MSAB）提升了特征解耦，使学生在某些任务上甚至超过教师。
• 优化的光谱分辨率（NFFT=256）在分类与检测之间取得平衡，在各任务上表现出强大性能。
• BioME 在蜂巢监测的边缘性能表现强劲，呈现出一种反向扩展趋势，即最小模型在 BSTS 上可能优于较大变体。

Figure 2: Block diagram of a single Transformer layer in the proposed BioME encoder. Patch embeddings are processed alongside side-channel context features, which are integrated at each layer through the Conditioner module implementing FiLM-based conditioning.