{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:08:10Z","timestamp":1765544890281,"version":"build-2065373602"},"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\/icassp49357.2023.10096526","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":7,"title":["A Novel Metric For Evaluating Audio Caption Similarity"],"prefix":"10.1109","author":[{"given":"Swapnil","family":"Bhosale","sequence":"first","affiliation":[{"name":"Tata Consultancy Services Limited,TCS Research,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rupayan","family":"Chakraborty","sequence":"additional","affiliation":[{"name":"Tata Consultancy Services Limited,TCS Research,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sunil Kumar","family":"Kopparapu","sequence":"additional","affiliation":[{"name":"Tata Consultancy Services Limited,TCS Research,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170058"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683490"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874013"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84882-054-8_7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2778423"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959998"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/08839514.2018.1430469"},{"key":"ref8","article-title":"BLEU: a method for Automatic Evaluation of Machine Translation","author":"Papineni","year":"2002","journal-title":"ACL"},{"key":"ref9","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"article-title":"METEOR: An Automatic metric for MT Evaluation with improved correlation with human judgments","volume-title":"ACL workshop on Intrinsic and Extrinsic Evaluation measures for Machine Translation and\/or Summarization","author":"Banerjee","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.33682\/sezz-vd31"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"article-title":"textacy: NLP, before and after spaCy,","year":"2020","author":"Honnibal","key":"ref15"},{"article-title":"spaCy: Industrial-strength Natural Language Processing in Python,","year":"2020","author":"DeWilde","key":"ref16"},{"article-title":"A CRNN-GRU Based Reinforcement Learning Approach to Audio Captioning","volume-title":"Detection and Classification of Acoustic Scenes and Events Workshop (DCASE)","author":"Xu","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682632"},{"key":"ref19","article-title":"BERTScore: Evaluating text generation with BERT","author":"Zhang","year":"2020","journal-title":"ICLR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414834"},{"key":"ref21","article-title":"Freesound datasets: a platform for the creation of open audio datasets","author":"Fonseca","year":"2017","journal-title":"International Society for Music Information Retrieval (ISMIR)"},{"key":"ref22","article-title":"The NTT DCASE2020 challenge task 6 system: Automated audio captioning with keywords and sentence length estimation","author":"Koizumi","year":"2020","journal-title":"DCASE Challenge"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","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\/10096526.pdf?arnumber=10096526","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:45:54Z","timestamp":1705016754000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096526\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096526","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}