{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T03:42:49Z","timestamp":1768966969679,"version":"3.49.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413982","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"905-909","source":"Crossref","is-referenced-by-count":26,"title":["Investigating Local and Global Information for Automated Audio Captioning with Transfer Learning"],"prefix":"10.1109","author":[{"given":"Xuenan","family":"Xu","sequence":"first","affiliation":[]},{"given":"Heinrich","family":"Dinkel","sequence":"additional","affiliation":[]},{"given":"Mengyue","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Zeyu","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Kai","family":"Yu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref12","first-page":"119","article-title":"Audiocaps: Generating captions for audios in the wild","author":"kim","year":"2019","journal-title":"Proc Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref14","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref15","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annual Meeting of the Association for Computational Linguistics (ACL)"},{"key":"ref16","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref17","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proc acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref4","first-page":"21","article-title":"Audio Captioning Based On Transformer And Pre-trained CNN","author":"wu","year":"2020","journal-title":"Proc Detection and Classification of Acoustic Scenes and Events Workshop (DCASE)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2087"},{"key":"ref6","first-page":"6","article-title":"Multi-task regularization based on infrequent classes for audio captioning","author":"\u00e7ak?r","year":"2020","journal-title":"Proc Detection and Classification of Acoustic Scenes and Events Workshop (DCASE)"},{"key":"ref5","first-page":"225","article-title":"A crnn-gru based reinforcement learning approach to audio captioning","author":"xu","year":"2020","journal-title":"Proc Detection and Classification of Acoustic Scenes and Events Workshop (DCASE)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682377"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170058"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053459"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952265"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413982.pdf?arnumber=9413982","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:57Z","timestamp":1652197257000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413982\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413982","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}