{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T12:07:49Z","timestamp":1725710869603},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,3]],"date-time":"2022-10-03T00:00:00Z","timestamp":1664755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,3]],"date-time":"2022-10-03T00:00:00Z","timestamp":1664755200000},"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":[[2022,10,3]]},"DOI":"10.1109\/icccnt54827.2022.9984255","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:44:09Z","timestamp":1672083849000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Web Framework for Enhancing Automated Audio Captioning Performance for Domestic Environment"],"prefix":"10.1109","author":[{"given":"Arushi","family":"Jain","sequence":"first","affiliation":[{"name":"Vellore Institute of Technology,Vellore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Navaneeth B","family":"R","sequence":"additional","affiliation":[{"name":"Vellore Institute of Technology,Vellore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shelly","family":"Mohanty","sequence":"additional","affiliation":[{"name":"Vellore Institute of Technology,Vellore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R.","family":"Sujatha","sequence":"additional","affiliation":[{"name":"Vellore Institute of Technology,Vellore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sujatha","family":"R","sequence":"additional","affiliation":[{"name":"Vellore Institute of Technology,Vellore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sourabh","family":"Tiwari","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute,Bangalore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rashmi T","family":"Shankarappa","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute,Bangalore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690563"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2930913"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3019702"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2895254"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3014737"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3090678"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2326181"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-140"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170058"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.33682\/7bay-bj41"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1011"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413982"},{"key":"ref15","first-page":"21","article-title":"Audio captioning based on transformer and pretrained cnn","volume-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events Workshop","author":"Chen"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/INDICON49873.2020.9342199"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCNT51525.2021.9579677"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616340"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2087"},{"key":"ref20","first-page":"225","article-title":"A crnn-gru based reinforcement learning approach to audio captioning","volume-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events Workshop","author":"Xu"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1121\/1.2972136"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/DELCON54057.2022.9753535"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2007-612"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCNT49239.2020.9225390"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/INDICON49873.2020.9342434"},{"author":"Mei","key":"ref26","article-title":"Audio Captioning Transformer"}],"event":{"name":"2022 13th International Conference on Computing Communication and Networking Technologies (ICCCNT)","start":{"date-parts":[[2022,10,3]]},"location":"Kharagpur, India","end":{"date-parts":[[2022,10,5]]}},"container-title":["2022 13th International Conference on Computing Communication and Networking Technologies (ICCCNT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9984157\/9984211\/09984255.pdf?arnumber=9984255","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T06:11:52Z","timestamp":1706767912000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9984255\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,3]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icccnt54827.2022.9984255","relation":{},"subject":[],"published":{"date-parts":[[2022,10,3]]}}}