{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:22:48Z","timestamp":1775229768568,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890325","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["DRCap: Decoding CLAP Latents with Retrieval-Augmented Generation for Zero-shot Audio Captioning"],"prefix":"10.1109","author":[{"given":"Xiquan","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,China"}]},{"given":"Wenxi","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,China"}]},{"given":"Ziyang","family":"Ma","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,China"}]},{"given":"Xuenan","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,China"}]},{"given":"Yuzhe","family":"Liang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,China"}]},{"given":"Zhisheng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,China"}]},{"given":"Qiuqiang","family":"Kong","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Electronics Engineering,China"}]},{"given":"Xie","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-022-00259-2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3321968"},{"key":"ref3","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. NeurIPS","author":"Sutskever"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096877"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1564"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448030"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447215"},{"key":"ref8","article-title":"Sjtu-thu automated audio captioning system for dcase 2024","volume-title":"Tech. Rep, Tech. Rep.","author":"Chen","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/421"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref13","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref14","article-title":"Diversity and bias in audio captioning datasets","author":"Martin Morato","year":"2021","journal-title":"DCASE"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448115"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3567770"},{"key":"ref17","article-title":"Weakly-supervised automated audio captioning via text only training","author":"Kouzelis","year":"2023"},{"key":"ref18","article-title":"Zero-shot audio captioning with audio-language model guidance and audio context keywords","author":"Salewski","year":"2023"},{"key":"ref19","article-title":"Zero-shot audio captioning via audibility guidance","author":"Shaharabany","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448504"},{"key":"ref23","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume-title":"Proc. NeurIPS","author":"Liang"},{"key":"ref24","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref25","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90% ChatGPT quality, march 2023","author":"Chiang","year":"2023"},{"key":"ref26","article-title":"DeCap: Decoding clip latents for zero-shot captioning via text-only training","author":"Li","year":"2023"},{"key":"ref27","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. NeurIPS","author":"Lewis"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446672"},{"key":"ref29","article-title":"Audiocaps: Generating captions for audios in the wild","volume-title":"Proc. NAACL","author":"Kim"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3419446"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889473"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414579"},{"key":"ref35","article-title":"Introducing ChatGPT","author":"Schulman","year":"2022","journal-title":"OpenAI Blog"},{"key":"ref36","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref37","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746427"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890325.pdf?arnumber=10890325","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:38Z","timestamp":1774416398000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890325\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890325","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}