{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T10:54:21Z","timestamp":1768560861510,"version":"3.49.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Newton Institutional Links Award from the British Council"},{"name":"Automated Captioning of Image and Audio for Visually and Hearing Impaired","award":["623805725"],"award-info":[{"award-number":["623805725"]}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/T019751\/1"],"award-info":[{"award-number":["EP\/T019751\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Scholarship from the China Scholarship Council","award":["202006470010"],"award-info":[{"award-number":["202006470010"]}]},{"name":"Creative Commons Attribution (CC BY) licence to any Author Accepted Manuscript version arising"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3416686","type":"journal-article","created":{"date-parts":[[2024,6,21]],"date-time":"2024-06-21T18:07:50Z","timestamp":1718993270000},"page":"3311-3323","source":"Crossref","is-referenced-by-count":2,"title":["Towards Generating Diverse Audio Captions via Adversarial Training"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6079-5130","authenticated-orcid":false,"given":"Xinhao","family":"Mei","sequence":"first","affiliation":[{"name":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9950-2672","authenticated-orcid":false,"given":"Xubo","family":"Liu","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianyuan","family":"Sun","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9708-1075","authenticated-orcid":false,"given":"Mark D.","family":"Plumbley","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8393-5703","authenticated-orcid":false,"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-022-00259-2"},{"key":"ref2","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Kim","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref4","first-page":"90","article-title":"Diversity and bias in audio captioning datasets","volume-title":"Proc. 6th Detection Classification Acoust. Scenes Events Workshop","author":"Martin","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170058"},{"key":"ref6","first-page":"225","article-title":"A CRNN-GRU based reinforcement learning approach to audio captioning","volume-title":"Proc. 5th Detection Classification Acoust. Scenes Events Workshop","author":"Xu","year":"2020"},{"key":"ref7","first-page":"21","article-title":"Audio captioning based on Transformer and pre-trained CNN","volume-title":"Proc. 5th Detection Classification Acoust. Scenes Events Workshop","author":"Chen","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2087"},{"key":"ref9","first-page":"40","article-title":"Improving the performance of automated audio captioning via integrating the acoustic and semantic information","volume-title":"Proc. 6th Detection Classification Acoust. Scenes Events Workshop","author":"Ye","year":"2021"},{"key":"ref10","first-page":"6","article-title":"Automated audio captioning with weakly supervised pre-training and word selection methods","volume-title":"Proc. 6th Detection Classification Acoust. Scenes Events Workshop","author":"Han","year":"2021"},{"key":"ref11","first-page":"211","article-title":"Audio captioning transformer","volume-title":"Proc. 6th Detection Classification Acoust. Scenes Events Workshop","author":"Mei","year":"2021"},{"key":"ref12","first-page":"206","article-title":"An encoder-decoder based audio captioning system with transfer and reinforcement learning","volume-title":"Proc. 6th Detection Classification Acoust. Scenes Events Workshop","author":"Mei","year":"2021"},{"key":"ref13","first-page":"196","article-title":"CL4AC: A contrastive loss for audio captioning","volume-title":"Proc. 6th Detection Classification Acoust. Scenes Events Workshop","author":"Liu","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909761"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3189536"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10510"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.445"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10804"},{"key":"ref25","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton","year":"2000"},{"key":"ref26","article-title":"GPT-4 Technical Report","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746894"},{"key":"ref28","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Sutskever","year":"2014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref30","first-page":"110","article-title":"Temporal sub-sampling of audio feature sequences for automated audio captioning","volume-title":"Proc. 5th Detection Classification Acoust. Scenes Events Workshop","author":"Nguyen","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362117"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.33682\/7bay-bj41"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2930913"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3014737"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.23919\/eusipco54536.2021.9616340"},{"key":"ref39","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746427"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413982"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7952261"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.323"},{"key":"ref45","article-title":"Generating diverse and accurate visual captions by comparative adversarial learning","volume-title":"Proc. NIPS Workshop Visually Grounded Interact. Lang.","author":"Li","year":"2018"},{"key":"ref46","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume-title":"Proc. NIPS Deep Learn. Workshop","author":"Chung","year":"2014"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10568388.pdf?arnumber=10568388","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T04:40:05Z","timestamp":1719895205000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10568388\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3416686","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}