Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.18452 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912944104669184 |
|---|---|
| author | Bertolino, Gaia A. Zhang, Yuwei Xia, Tong Talia, Domenico Mascolo, Cecilia |
| author_facet | Bertolino, Gaia A. Zhang, Yuwei Xia, Tong Talia, Domenico Mascolo, Cecilia |
| contents | As conversational multimodal AI tools are increasingly adopted to process patient data for health assessment, robust benchmarks are needed to measure progress and expose failure modes under realistic conditions. Despite the importance of respiratory audio for mobile health screening, respiratory audio question answering remains underexplored, with existing studies evaluated narrowly and lacking real-world heterogeneity across modalities, devices, and question types. We hence introduce the Respiratory-Audio Question-Answering (RA-QA) benchmark, including a standardized data generation pipeline, a comprehensive multimodal QA collection, and a unified evaluation protocol. RA-QA harmonizes public RA datasets into a collection of 9 million format-diverse QA pairs covering diagnostic and contextual attributes. We benchmark classical ML baselines alongside multimodal audio-language models, establishing reproducible reference points and showing how current approaches fail under heterogeneity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_18452 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RA-QA: A Benchmarking System for Respiratory Audio Question Answering Under Real-World Heterogeneity Bertolino, Gaia A. Zhang, Yuwei Xia, Tong Talia, Domenico Mascolo, Cecilia Sound Machine Learning Audio and Speech Processing As conversational multimodal AI tools are increasingly adopted to process patient data for health assessment, robust benchmarks are needed to measure progress and expose failure modes under realistic conditions. Despite the importance of respiratory audio for mobile health screening, respiratory audio question answering remains underexplored, with existing studies evaluated narrowly and lacking real-world heterogeneity across modalities, devices, and question types. We hence introduce the Respiratory-Audio Question-Answering (RA-QA) benchmark, including a standardized data generation pipeline, a comprehensive multimodal QA collection, and a unified evaluation protocol. RA-QA harmonizes public RA datasets into a collection of 9 million format-diverse QA pairs covering diagnostic and contextual attributes. We benchmark classical ML baselines alongside multimodal audio-language models, establishing reproducible reference points and showing how current approaches fail under heterogeneity. |
| title | RA-QA: A Benchmarking System for Respiratory Audio Question Answering Under Real-World Heterogeneity |
| topic | Sound Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2602.18452 |