{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T10:11:05Z","timestamp":1783937465319,"version":"3.55.0"},"reference-count":22,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747676","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7722-7726","source":"Crossref","is-referenced-by-count":17,"title":["Automated Audio Captioning Using Transfer Learning and Reconstruction Latent Space Similarity Regularization"],"prefix":"10.1109","author":[{"given":"Andrew","family":"Koh","sequence":"first","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue","family":"Fuzhao","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chng Eng","family":"Siong","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053459"},{"key":"ref11","article-title":"Audio captioning transformer","author":"mei","year":"2021"},{"key":"ref12","article-title":"Audio Captioning using Pre-Trained Large-Scale Language Model Guided by Audio-based Similar Caption Retrieval","author":"koizumi","year":"2020"},{"key":"ref13","article-title":"Bertscore: Evaluating text generation with bert","author":"zhang","year":"2020"},{"key":"ref14","article-title":"Audio Captioning using Gated Recurrent Units","author":"eren","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref17","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2015"},{"key":"ref18","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":"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","article-title":"Attention is all you need","author":"vaswani","year":"2017"},{"key":"ref3","article-title":"Clotho: An Audio Captioning Dataset","author":"drossos","year":"2019"},{"key":"ref6","first-page":"119","article-title":"AudioCaps: Generating Captions for Audios in The Wild","author":"kim","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies Volume 1 (Long and Short Papers)"},{"key":"ref5","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019"},{"key":"ref8","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 2020 Workshop (DCASE2020)"},{"key":"ref7","article-title":"Audio Caption in a Car Setting with a Sentence-Level Loss","author":"xu","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170058"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413982"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-46454-1_24","article-title":"Spice: Semantic propositional image caption evaluation","author":"anderson","year":"2016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"}],"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\/09747676.pdf?arnumber=9747676","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:10:25Z","timestamp":1660594225000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747676\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747676","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}