{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:18:13Z","timestamp":1776885493990,"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\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000308","name":"British Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000308","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","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\/icassp43922.2022.9746894","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8882-8886","source":"Crossref","is-referenced-by-count":20,"title":["Diverse Audio Captioning Via Adversarial Training"],"prefix":"10.1109","author":[{"given":"Xinhao","family":"Mei","sequence":"first","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xubo","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianyuan","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark D.","family":"Plumbley","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"905","article-title":"Investigating local and global information for automated audio captioning with transfer learning","author":"xu","year":"2021","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref11","first-page":"21","article-title":"Audio captioning based on Transformer and pre-trained CNN","author":"chen","year":"2020","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events Workshop"},{"key":"ref12","article-title":"Audio captioning Transformer","author":"mei","year":"2021","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events Workshop"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2087"},{"key":"ref14","article-title":"Improving the performance of automated audio captioning via integrating the acoustic and textual information","author":"ye","year":"2021","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref15","article-title":"Audio captioning using pre-trained large-scale language model guided by audio-based similar caption retrieval","author":"koizumi","year":"2020"},{"key":"ref16","article-title":"CL4AC: A contrastive loss for audio captioning","author":"liu","year":"2021","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events Workshop"},{"key":"ref17","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems"},{"key":"ref18","article-title":"An encoder-decoder based audio captioning system with transfer and reinforcement learning","author":"mei","year":"2021","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events Workshop"},{"key":"ref19","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref4","first-page":"311","article-title":"BLEU: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics  - ACL '02"},{"key":"ref3","first-page":"736","article-title":"Clotho: An audio captioning dataset","author":"drossos","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref6","article-title":"Generative adversarial nets","volume":"27","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref8","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10804"},{"key":"ref2","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","author":"kim","year":"2019","journal-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170058"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref20","first-page":"382","article-title":"SPICE: Semantic propositional image caption evaluation","author":"anderson","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref22","article-title":"Generating diverse and accurate visual captions by comparative adversarial learning","author":"li","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.323"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.445"},{"key":"ref25","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014"}],"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\/09746894.pdf?arnumber=9746894","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:08:55Z","timestamp":1660594135000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746894\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746894","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}