{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:10:37Z","timestamp":1776888637394,"version":"3.51.2"},"reference-count":32,"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\/icassp48485.2024.10446672","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"6735-6739","source":"Crossref","is-referenced-by-count":21,"title":["EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning"],"prefix":"10.1109","author":[{"given":"Jaeyeon","family":"Kim","sequence":"first","affiliation":[{"name":"MAUM AI Inc.,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaeyoon","family":"Jung","sequence":"additional","affiliation":[{"name":"MAUM AI Inc.,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinjoo","family":"Lee","sequence":"additional","affiliation":[{"name":"MAUM AI Inc.,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sang Hoon","family":"Woo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170058"},{"key":"ref2","article-title":"AudioCaps: Generating captions for audios in the wild","author":"Kim","year":"2019","journal-title":"NAACL"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref4","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015"},{"key":"ref5","article-title":"Audio captioning transformer","volume-title":"DCASE Workshop","author":"Mei"},{"key":"ref6","article-title":"Improving the performance of automated audio captioning via integrating the acoustic and semantic information","author":"Ye","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3189536"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3266114"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1564"},{"key":"ref10","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref11","article-title":"Audio captioning using pre-trained large-scale language model guided by audio-based similar caption retrieval","author":"Koizumi","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096877"},{"key":"ref13","article-title":"Pengi: An audio language model for audio tasks","author":"Deshmukh","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref15","article-title":"Automated audio captioning by fine-tuning bart with audioset tags","volume-title":"DCASE Workshop","author":"Gontier"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2087"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO58844.2023.10290108"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref19","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-943"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref24","article-title":"Exploring train and test-time augmentations for audio-language learning","author":"Kim","year":"2022"},{"key":"ref25","article-title":"Wav-caps: A chatgpt-assisted weakly-labelled audio captioning dataset for audio-language multimodal research","author":"Mei","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10510"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref29","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"Banerjee","year":"2005","journal-title":"ACL"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"}],"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\/10446672.pdf?arnumber=10446672","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:24:47Z","timestamp":1722576287000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446672\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446672","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}