{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:21:43Z","timestamp":1775229703393,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10097021","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":6,"title":["Spice+: Evaluation of Automatic Audio Captioning Systems with Pre-Trained Language Models"],"prefix":"10.1109","author":[{"given":"F\u00e9lix","family":"Gontier","sequence":"first","affiliation":[{"name":"Université de Lorraine, CNRS, Inria,Loria,France,F-54000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Romain","family":"Serizel","sequence":"additional","affiliation":[{"name":"Université de Lorraine, CNRS, Inria,Loria,France,F-54000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christophe","family":"Cerisara","sequence":"additional","affiliation":[{"name":"Université de Lorraine, CNRS, Inria,Loria,France,F-54000"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Is my automatic captioning system so bad? spidermax: a metric to consider several caption candidates","author":"labb\u00e9","year":"2022","journal-title":"2022 Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref12","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","author":"kim","year":"2019","journal-title":"2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies Volume 1 (Long and Short Papers)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746427"},{"key":"ref20","first-page":"1","article-title":"CoNLL 2018 shared task: Multilingual parsing from raw text to Universal Dependencies","author":"zeman","year":"2018","journal-title":"Proc CoNLL 2018 Shared Task Multilingual Parsing from Raw Text to Universal Dependencies"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref22","article-title":"Mpnet: Masked and permuted pre-training for language understanding","author":"song","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1279"},{"key":"ref2","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"40th Annual Meeting of the Association for Computational Linguistics"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170058"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref16","article-title":"A summarization approach to evaluating audio captioning","author":"mart\u00edn-morat\u00f3","year":"2022","journal-title":"2022 Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/1075096.1075150"},{"key":"ref18","first-page":"4034","article-title":"Universal Dependencies v2: An evergrowing multilingual treebank collection","author":"nivre","year":"2020","journal-title":"Language Resources and Evaluation Conference"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995466"},{"key":"ref9","first-page":"382","article-title":"Spice: Semantic propositional image caption evaluation","author":"anderson","year":"2016","journal-title":"ECC 2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2074"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10097021.pdf?arnumber=10097021","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:05:21Z","timestamp":1700507121000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097021\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10097021","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}