{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T10:34:21Z","timestamp":1768559661000,"version":"3.49.0"},"reference-count":29,"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":[{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["Z200002"],"award-info":[{"award-number":["Z200002"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225601"],"award-info":[{"award-number":["62225601"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2052"],"award-info":[{"award-number":["U23B2052"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Youth Innovative Research Team of BUPT","award":["2023QNTD02"],"award-info":[{"award-number":["2023QNTD02"]}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["202306470064"],"award-info":[{"award-number":["202306470064"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/lsp.2024.3409212","type":"journal-article","created":{"date-parts":[[2024,6,4]],"date-time":"2024-06-04T21:37:25Z","timestamp":1717537045000},"page":"2520-2524","source":"Crossref","is-referenced-by-count":3,"title":["Generating Accurate and Diverse Audio Captions Through Variational Autoencoder Framework"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1172-6846","authenticated-orcid":false,"given":"Yiming","family":"Zhang","sequence":"first","affiliation":[{"name":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8372-5637","authenticated-orcid":false,"given":"Ruoyi","family":"Du","sequence":"additional","affiliation":[{"name":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6856-8928","authenticated-orcid":false,"given":"Zheng-Hua","family":"Tan","sequence":"additional","affiliation":[{"name":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark"}],"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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2950-2488","authenticated-orcid":false,"given":"Zhanyu","family":"Ma","sequence":"additional","affiliation":[{"name":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170058"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2087"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-022-00259-2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3321968"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362117"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3293015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.33682\/sezz-vd31"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096877"},{"key":"ref10","article-title":"IRIT-UPS DCASE 2022 task6a system: Stochastic decoding methods for audio captioning","author":"Labb","year":"2022"},{"key":"ref11","first-page":"40","article-title":"Improving the performance of automated audio captioning via integrating the acoustic and textual information","volume-title":"Proc. Workshop Detection Classification Acoust. Scenes Events","author":"Ye","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-914"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747676"},{"key":"ref14","first-page":"225","article-title":"A based reinforcement learning approach to audio captioning","volume-title":"Proc. Workshop Detection Classification Acoust. Scenes Events","author":"Xu","year":"2020"},{"key":"ref15","first-page":"206","article-title":"An encoder-decoder based audio captioning system with transfer and reinforcement learning","volume-title":"Proc. Workshop Detection Classification Acoust. Scenes Events","author":"Mei","year":"2021"},{"key":"ref16","first-page":"196","article-title":"CL4AC: A contrastive loss for audio captioning","volume-title":"Proc. Workshop Detection Classification Acoust. Scenes Events","author":"Liu","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10510"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3189536"},{"key":"ref19","first-page":"6","article-title":"Automated audio captioning with weakly supervised pre-training and word selection methods","volume-title":"Proc. Workshop Detection Classification Acoust. Scenes Events","author":"Han","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746894"},{"key":"ref21","article-title":"Towards generating diverse audio captions via adversarial training","author":"Mei","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746834"},{"key":"ref23","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref24","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn","year":"2015"},{"key":"ref25","first-page":"5758","article-title":"Diverse and accurate image description using a variational auto-encoder with an additive gaussian encoding space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3614435"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref29","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10380231\/10547425.pdf?arnumber=10547425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,25]],"date-time":"2024-09-25T19:33:48Z","timestamp":1727292828000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10547425\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/lsp.2024.3409212","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}