{"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":1776885493851,"version":"3.51.2"},"reference-count":24,"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\/icassp43922.2022.9746427","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"981-985","source":"Crossref","is-referenced-by-count":27,"title":["Can Audio Captions Be Evaluated With Image Caption Metrics?"],"prefix":"10.1109","author":[{"given":"Zelin","family":"Zhou","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China"}]},{"given":"Zhiling","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China"}]},{"given":"Xuenan","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China"}]},{"given":"Zeyu","family":"Xie","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China"}]},{"given":"Mengyue","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China"}]},{"given":"Kenny Q.","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref10","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref12","first-page":"382","article-title":"Spice: Semantic propositional image caption evaluation","author":"anderson","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1238"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1060"},{"key":"ref15","article-title":"Bertscore: Evaluating text generation with bert","author":"zhang","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.704"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413982"},{"key":"ref4","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682377"},{"key":"ref6","article-title":"An encoder-decoder based audio captioning system with transfer and reinforcement learning for dcase challenge 2021 task 6","author":"mei","year":"2021","journal-title":"DCASE2021 Challenge Tech Rep Tech Rep"},{"key":"ref5","article-title":"The sjtu system for dcase2021 challenge task 6: Audio captioning based on encoder pre-training and reinforcement learning","author":"xu","year":"2021","journal-title":"DCASE2021 Challenge Tech Rep Tech Rep"},{"key":"ref8","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":"ref7","first-page":"225","article-title":"A crnn-gru based reinforcement learning approach to audio captioning","author":"xu","year":"2020","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events Workshop (DCASE)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref9","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170058"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12340"},{"key":"ref22","first-page":"4171","article-title":"Bert: Pretraining of deep bidirectional transformers for language understanding","author":"devlin","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":"ref21","doi-asserted-by":"publisher","DOI":"10.1037\/h0031619"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1220"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482097"}],"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\/09746427.pdf?arnumber=9746427","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:12:57Z","timestamp":1661199177000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746427\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746427","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}