Abstract
Text-to-Audio (T2A) retrievers are typically evaluated with caption style queries, but the same user intent can be expressed in many forms. We introduce CORA (Caption-Offset Retrieval for Audio), a caption anchored diagnostic protocol that rewrites each source caption into five intent preserving forms (Command, Question, Indirect, Key phrase, and Statement) while fixing the target audio. By tracking the same target across query forms, CORA defines RankDrop, a metric revealing failures hidden by Recall@k. Using Pearson's correlation coefficient r, we find that RankDrop is weakly associated with raw text space movement (r=0.084), but strongly associated with Target Alignment Loss and Target Boundary Margin Degradation (r=0.508 and r=0.615). The same pattern appears in OEA retrievers, where RankDrop is better explained by boundary degradation (r=0.472/0.478) than by query movement (r=0.084/0.046). Overall, these results suggest that robust T2A retrieval requires preserving the target's boundary advantage over competing audio under reformulation.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Woo, J. M., Kong, K., Jeong, B., Kim, M., Yoo, H., & Chang, D. S. (2026). CORA: A Protocol for Diagnosing Boundary Robustness in Text-to-Audio Retrieval under Query Reformulations. https://omanscience.com/en/articles/cora-a-protocol-for-diagnosing-boundary-robustness-in-text-to-audio-retrieval-under-query-reformulations
MLA 9
Woo, Jae Min, et al. "CORA: A Protocol for Diagnosing Boundary Robustness in Text-to-Audio Retrieval under Query Reformulations." https://omanscience.com/en/articles/cora-a-protocol-for-diagnosing-boundary-robustness-in-text-to-audio-retrieval-under-query-reformulations.
Chicago (author–date)
Woo, Jae Min, Kyongmin Kong, Bogyung Jeong, Minjeong Kim, HaeJun Yoo, and Du-Seong Chang. 2026. "CORA: A Protocol for Diagnosing Boundary Robustness in Text-to-Audio Retrieval under Query Reformulations." https://omanscience.com/en/articles/cora-a-protocol-for-diagnosing-boundary-robustness-in-text-to-audio-retrieval-under-query-reformulations.
Harvard
Woo, J. M., Kong, K., Jeong, B., Kim, M., Yoo, H. and Chang, D. S. (2026) 'CORA: A Protocol for Diagnosing Boundary Robustness in Text-to-Audio Retrieval under Query Reformulations', Available at: https://omanscience.com/en/articles/cora-a-protocol-for-diagnosing-boundary-robustness-in-text-to-audio-retrieval-under-query-reformulations.
Vancouver
Woo JM, Kong K, Jeong B, Kim M, Yoo H, Chang DS. CORA: A Protocol for Diagnosing Boundary Robustness in Text-to-Audio Retrieval under Query Reformulations. https://omanscience.com/en/articles/cora-a-protocol-for-diagnosing-boundary-robustness-in-text-to-audio-retrieval-under-query-reformulations
IEEE
J. M. Woo, K. Kong, B. Jeong, M. Kim, H. Yoo, and D. S. Chang, "CORA: A Protocol for Diagnosing Boundary Robustness in Text-to-Audio Retrieval under Query Reformulations," https://omanscience.com/en/articles/cora-a-protocol-for-diagnosing-boundary-robustness-in-text-to-audio-retrieval-under-query-reformulations.