Research

Paper

AI LLM March 06, 2026

RAMoEA-QA: Hierarchical Specialization for Robust Respiratory Audio Question Answering

Authors

Gaia A. Bertolino, Yuwei Zhang, Tong Xia, Domenico Talia, Cecilia Mascolo

Abstract

Conversational generative AI is rapidly entering healthcare, where general-purpose models must integrate heterogeneous patient signals and support diverse interaction styles while producing clinically meaningful outputs. In respiratory care, non-invasive audio, such as recordings captured via mobile microphones, enables scalable screening and longitudinal monitoring, but the heterogeneity challenge is particularly acute: recordings vary widely across devices, environments, and acquisition protocols, and questions span multiple intents and question formats. Existing biomedical audio-language QA systems are typically monolithic, without any specialization mechanisms for tackling diverse respiratory corpora and query intents. They are also only validated in limited settings, leaving it unclear how reliably they handle the shifts encountered in real-world settings. To address these limitations, we introduce RAMoEA-QA, a hierarchically routed generative model for respiratory audio question answering that unifies multiple question types and supports both discrete and continuous targets within a single multimodal system. RAMoEA-QA applies two-stage conditional specialization: an Audio Mixture-of-Experts routes each recording to a suitable pre-trained audio encoder, and a Language Mixture-of-Adapters selects a LoRA adapter on a shared frozen LLM to match the query intent and answer format. By specializing both acoustic representations and generation behaviour per example, RAMoEA-QA consistently outperforms strong baselines and routing ablations with minimal parameter overhead, improving in-domain test accuracy to 0.72 (vs. 0.61 and 0.67 for state-of-the-art baselines) and exhibiting the strongest generalization for diagnosis under domain, modality, and task shifts.

Metadata

arXiv ID: 2603.06542
Provider: ARXIV
Primary Category: cs.SD
Published: 2026-03-06
Fetched: 2026-03-09 06:05

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.06542v1</id>\n    <title>RAMoEA-QA: Hierarchical Specialization for Robust Respiratory Audio Question Answering</title>\n    <updated>2026-03-06T18:29:15Z</updated>\n    <link href='https://arxiv.org/abs/2603.06542v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.06542v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Conversational generative AI is rapidly entering healthcare, where general-purpose models must integrate heterogeneous patient signals and support diverse interaction styles while producing clinically meaningful outputs. In respiratory care, non-invasive audio, such as recordings captured via mobile microphones, enables scalable screening and longitudinal monitoring, but the heterogeneity challenge is particularly acute: recordings vary widely across devices, environments, and acquisition protocols, and questions span multiple intents and question formats. Existing biomedical audio-language QA systems are typically monolithic, without any specialization mechanisms for tackling diverse respiratory corpora and query intents. They are also only validated in limited settings, leaving it unclear how reliably they handle the shifts encountered in real-world settings.\n  To address these limitations, we introduce RAMoEA-QA, a hierarchically routed generative model for respiratory audio question answering that unifies multiple question types and supports both discrete and continuous targets within a single multimodal system. RAMoEA-QA applies two-stage conditional specialization: an Audio Mixture-of-Experts routes each recording to a suitable pre-trained audio encoder, and a Language Mixture-of-Adapters selects a LoRA adapter on a shared frozen LLM to match the query intent and answer format. By specializing both acoustic representations and generation behaviour per example, RAMoEA-QA consistently outperforms strong baselines and routing ablations with minimal parameter overhead, improving in-domain test accuracy to 0.72 (vs. 0.61 and 0.67 for state-of-the-art baselines) and exhibiting the strongest generalization for diagnosis under domain, modality, and task shifts.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.SD'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-06T18:29:15Z</published>\n    <arxiv:primary_category term='cs.SD'/>\n    <author>\n      <name>Gaia A. Bertolino</name>\n    </author>\n    <author>\n      <name>Yuwei Zhang</name>\n    </author>\n    <author>\n      <name>Tong Xia</name>\n    </author>\n    <author>\n      <name>Domenico Talia</name>\n    </author>\n    <author>\n      <name>Cecilia Mascolo</name>\n    </author>\n  </entry>"
}