{"paper":{"title":"DiffATR: Diffusion-based Generative Modeling for Audio-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","eess.AS"],"primary_cat":"cs.SD","authors_text":"Xusheng Yang, Xuxin Cheng, Yifei Xin, Yuexian Zou, Zhihong Zhu","submitted_at":"2024-09-16T06:33:26Z","abstract_excerpt":"Existing audio-text retrieval (ATR) methods are essentially discriminative models that aim to maximize the conditional likelihood, represented as p(candidates|query). Nevertheless, this methodology fails to consider the intrinsic data distribution p(query), leading to difficulties in discerning out-of-distribution data. In this work, we attempt to tackle this constraint through a generative perspective and model the relationship between audio and text as their joint probability p(candidates,query). To this end, we present a diffusion-based ATR framework (DiffATR), which models ATR as an iterat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10025","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.10025/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}