{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T20:45:58Z","timestamp":1782420358372,"version":"3.54.5"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Basic Science Research Program through the National Research Foundation of Korea (NRF), funded by the Ministry of Education","award":["2020R1I1A3072457"],"award-info":[{"award-number":["2020R1I1A3072457"]}]},{"name":"Institute of Information and Communications Technology Planning and Evaluation (IITP) through the Information Technology Research Center (ITRC) Program, funded by the Korean Government","award":["IITP-2025-RS-2023-00259967"],"award-info":[{"award-number":["IITP-2025-RS-2023-00259967"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3704285","type":"journal-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T19:44:44Z","timestamp":1781639084000},"page":"93352-93369","source":"Crossref","is-referenced-by-count":0,"title":["Automatic Sound Effect Classification and Subtitle Generation System Using Pre-Trained Audio Neural Networks With Transfer Learning"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1461-1804","authenticated-orcid":false,"given":"Hyeyoon","family":"Jung","sequence":"first","affiliation":[{"name":"Department of Information Convergence Engineering, Pusan National University, Busan, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9948-2550","authenticated-orcid":false,"given":"Kyeongsu","family":"Byun","sequence":"additional","affiliation":[{"name":"Department of Information Convergence Engineering, Pusan National University, Busan, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8207-9415","authenticated-orcid":false,"given":"Joonho","family":"Kwon","sequence":"additional","affiliation":[{"name":"Department of Data Science, Graduate School of Data Science, Pusan National University, Busan, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.828699"},{"issue":"1","key":"ref2","first-page":"397","article-title":"Deep learning-based multi-sound classification for sound effect subtitle generation","volume-title":"Proc. Annu. Conf. Korea Inf. Process. Soc. (KIPS)","volume":"27","author":"Jung"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2657381"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3544639"},{"key":"ref6","volume-title":"Yamnet","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3392649"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCS48705.2020.9074180"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1614"},{"key":"ref10","volume-title":"Audio recognition using mel spectrograms and convolution neural networks.","author":"Zhang","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1142\/S0218127497001618"},{"issue":"5","key":"ref12","first-page":"427","article-title":"Deep learning and transfer learning approaches for image classification","volume":"7","author":"Krishna","year":"2019","journal-title":"Int. J. Recent Technol. Eng."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2018.03.032"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.091"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.4324\/9781315674278"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00607"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.201"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-5209"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-744"},{"key":"ref21","volume-title":"Audioset: A Large-Scale Dataset of Human-Labeled Audio Events","year":"2026"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3133208"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3389\/fnint.2020.00001"},{"key":"ref24","volume-title":"Netflix Timed Text Style Guide (General Requirements\/English","year":"2026"},{"key":"ref25","volume-title":"Captioning Key: Sound Effects and Music","year":"2026"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3577163.3595112"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2009.5403089"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11568463.pdf?arnumber=11568463","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T19:46:01Z","timestamp":1782416761000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11568463\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3704285","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}