用声音检测结核病，融合声学特征与深度模型，效果更优。
From Signals to Patterns: Non-Invasive Tuberculosis Detection from Cough Audio using Bandit Weighted Hyperbolic Prototypes
- 通过超球原型与带权融合，结合声学特征与预训练音频表示
- 在CODA TB数据集上超越单一特征与拼接方法，达到新最佳性能
- 适合医疗筛查、非侵入式疾病检测方向的研究者参考
本研究聚焦于基于咳嗽声音的结核病筛查（CBTS），假设将语音/音频基础表示与频谱描述符融合可提升筛查性能。我们预期这种融合能发挥互补优势：频谱特征保留咳嗽信号的短时精细声学细节，而基础嵌入则捕捉大规模预训练中学习到的高层次时间与事件模式。为此，我们提出COBALT框架，基于代码本对齐的双曲原型与带权可靠性加权机制，有效整合异构表示。在CODA TB DREAM挑战赛基准上，COBALT持续优于单一表示和拼接基线，在融合MFCC与PaSST时实现最佳整体性能，确立了该基准的新最优水平。
原文摘要 · Abstract (English)
In this study, we focus on cough-based tuberculosis screening (CBTS) and hypothesize that fusing speech/audio foundation representations with spectral descriptors will yield stronger screening performance. We expect this fusion to reveal complementary strengths: spectral features preserve fine-grained short-time acoustic detail in cough signals, while foundation embeddings capture higher-level temporal and event-level patterns learned from large-scale pretraining. To this end, we propose COBALT, a novel fusion framework based on codebook-aligned hyperbolic prototypes and bandit-style reliability weighting to integrate heterogeneous representations effectively. Using the CODA TB DREAM Challenge benchmark, COBALT consistently outperforms individual representations and a concatenation baseline, achieving the best overall performance when fusing MFCC with PaSST thereby establishing a new state-of-the-art on the benchmark.
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。