arXiv cs.AI· Xinhong Li, Weiping Tu·· 12 小时前AI 评分18
APRIL：面向呼吸音域增量学习的歧义感知专家路由框架
APRIL: Ambiguity-Aware Expert Routing for Respiratory Sound Domain-Incremental Learning
AI 导读
APRIL 是一个无需样本回放的呼吸音分类域增量学习框架，基于冻结的 BEATs 骨干网络顺序继承并隔离低秩专家，通过多级原型路由器检索 top-2 候选专家并按匹配歧义动态加权选择最终模型。在 ICBHI 和 SPRSound 上构建设备与时间增量基准，五个随机种子下最终会话平均 Score 分别达 64.4%/65.4% 和 83.1%/82.2%，所有协议平均遗忘均低于 1.0%。
正文 · 原文
Abstract:Automated respiratory sound classification enables continuous, non-invasive respiratory assessment, yet long-term deployment remains challenging due to domain shifts from evolving recording devices and acquisition periods. When privacy and governance regulations prohibit replaying historical data, sequential learning easily overwrites previously acquired knowledge. Preserving dedicated domain experts prevents parameter interference, but selecting the correct expert at inference is difficult under overlapping acoustic distributions and absent domain labels. To resolve this dilemma, we propose APRIL, an exemplar-free domain-incremental framework for RSC. Built on a shared frozen BEATs backbone, APRIL sequentially inherits and isolates low-rank experts to enable new-domain adaptation without altering earlier models. A multi-level prototype router retrieves the top-two candidate experts and dynamically selects the final model by integrating domain-routing posteriors with classification confidence, adaptively weighted by matching ambiguity. We establish standardized device- and temporal-incremental benchmarks on the ICBHI and SPRSound datasets across forward and reversed domain orders. Evaluated over five random seeds, APRIL consistently achieves the highest final-session average Score among compared continual learning approaches, reaching 64.4% and 65.4% on ICBHI, and 83.1% and 82.2% on SPRSound under forward and reversed sequences, respectively. Crucially, average forgetting remains under 1.0% across all protocols, demonstrating robust domain adaptation and long-term knowledge retention without data replay. Overall, APRIL offers a reliable and privacy-preserving paradigm for deploying continuous respiratory sound classification across real-world healthcare settings.
| Subjects: | Sound (cs.SD); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.27942 [cs.SD] |
| (or arXiv:2610.27942v1 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2610.27942 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xinhong Li [view email]
[v1]
Tue, 20 Oct 2026 09:49:56 UTC (1,438 KB)
来源：arXiv cs.AI · arxiv.org