{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:43:01Z","timestamp":1782834181150,"version":"3.54.5"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448030","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1161-1165","source":"Crossref","is-referenced-by-count":19,"title":["Recap: Retrieval-Augmented Audio Captioning"],"prefix":"10.1109","author":[{"given":"Sreyan","family":"Ghosh","sequence":"first","affiliation":[{"name":"University of Maryland,College Park,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sonal","family":"Kumar","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chandra Kiran","family":"Reddy Evuru","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramani","family":"Duraiswami","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dinesh","family":"Manocha","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref2","first-page":"119","article-title":"Audiocaps: Generating captions for audios in the wild","author":"Kim","journal-title":"ACL 2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3149712"},{"key":"ref5","article-title":"Automated audio captioning by fine-tuning bart with audioset tags","author":"Gontier","year":"2021","journal-title":"DCASE2021 Challenge"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096877"},{"key":"ref7","article-title":"Audio captioning using pre-trained large-scale language model guided by audio-based similar caption retrieval","author":"Koizumi","year":"2020"},{"key":"ref8","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","author":"Lewis","journal-title":"NeurIPS 2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2020.00014"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413982"},{"key":"ref11","article-title":"Beats-based audio captioning model with instructor embedding supervision and chatgpt mix-up","volume-title":"Tech. Rep., DCASE2023 Challenge","author":"Wu"},{"key":"ref12","article-title":"A whisper transformer for audio captioning trained with synthetic captions and transfer learning","author":"Kadl\u010d\u00edk","year":"2023"},{"key":"ref13","article-title":"Leveraging multi-task training and image retrieval with clap for audio captioning","volume-title":"Tech. Rep., DCASE2023 Challenge","author":"Sun"},{"key":"ref14","article-title":"Label-refined sequential training with noisy data for automated audio captioning","volume-title":"Tech. Rep., DCASE2023 Challenge","author":"Sim"},{"key":"ref15","first-page":"1533","article-title":"Semantic parsing on freebase from question-answer pairs","author":"Berant","journal-title":"EMNLP 2013"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3549555.3549585"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.266"},{"key":"ref19","article-title":"Audio captioning transformer","author":"Mei","journal-title":"DCASE2021 Challenge."},{"key":"ref20","first-page":"21","article-title":"Audio captioning based on transformer and pre-trained cnn","author":"Chen","year":"2020","journal-title":"DCASE"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747676"},{"key":"ref22","article-title":"Few-shot learning with retrieval augmented language models","author":"Izacard","year":"2022"},{"key":"ref23","article-title":"A survey on retrieval-augmented text generation","author":"Li","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448030.pdf?arnumber=10448030","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T06:38:42Z","timestamp":1722580722000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448030\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448030","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}