{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:18:14Z","timestamp":1776885494136,"version":"3.51.2"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746834","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"971-975","source":"Crossref","is-referenced-by-count":6,"title":["Diversity-Controllable and Accurate Audio Captioning Based on Neural Condition"],"prefix":"10.1109","author":[{"given":"Xuenan","family":"Xu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence X-LANCE Lab,Department of Computer Science and Engineering AI Institute,Shanghai,China"}]},{"given":"Mengyue","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence X-LANCE Lab,Department of Computer Science and Engineering AI Institute,Shanghai,China"}]},{"given":"Kai","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence X-LANCE Lab,Department of Computer Science and Engineering AI Institute,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00850"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2819941"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.323"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.445"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.33682\/7bay-bj41"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref16","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref18","first-page":"119","article-title":"Audiocaps: Generating captions for audios in the wild","author":"kim","year":"2019","journal-title":"Proceedings of Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)"},{"key":"ref19","article-title":"Averaging weights leads to wider optima and better generalization","author":"izmailov","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2087"},{"key":"ref3","article-title":"Audio captioning using pre-trained large-scale language model guided by audio-based similar caption retrieval","author":"koizumi","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682377"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2020.00014"},{"key":"ref8","first-page":"5758","article-title":"Diverse and accurate image description using a variational auto-encoder with an additive gaussian encoding space","author":"wang","year":"2017","journal-title":"Proceedings of Conference on Neural Information Processing Systems (NIPS)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1014"},{"key":"ref2","first-page":"21","article-title":"Audio captioning based on transformer and pretrained cnn","author":"chen","year":"2020","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events Workshop (DCASE)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12340"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413982"},{"key":"ref20","first-page":"311","article-title":"BLEU: a Method for Automatic Evaluation of Machine Translation","author":"kishore","year":"2002","journal-title":"Proc Ann Meeting on Assoc for Computational Linguistics (ACL)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref21","first-page":"25","article-title":"Rouge: A package for automatic evaluation of summaries","author":"chin-yew","year":"2004","journal-title":"Proceedings of the Workshop on Text Summarization Branches Out"},{"key":"ref24","first-page":"382","article-title":"SPICE: Semantic propositional image caption evaluation","author":"anderson","year":"2016","journal-title":"Proceedings of European Conference on Computer Vision (ECCV)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210080"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746834.pdf?arnumber=9746834","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:10:37Z","timestamp":1660594237000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746834\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746834","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}