{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:38:24Z","timestamp":1730230704485,"version":"3.28.0"},"reference-count":25,"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\/icassp49357.2023.10094658","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["SLBERT: A Novel Pre-Training Framework for Joint Speech and Language Modeling"],"prefix":"10.1109","author":[{"given":"Onkar","family":"Susladkar","sequence":"first","affiliation":[{"name":"Natter Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prajwal","family":"Gatti","sequence":"additional","affiliation":[{"name":"Dayananda Sagar College of Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Santosh","family":"Kumar Yadav","sequence":"additional","affiliation":[{"name":"Natter Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"devlin","key":"ref13"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00521"},{"article-title":"Roberta: A robustly optimized bert pretraining approach","year":"2019","author":"liu","key":"ref15"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref11","article-title":"Vil-bert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"article-title":"Speechbert: An audio-and-text jointly learned language model for end-to-end spoken question answering","year":"2019","author":"chuang","key":"ref10"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/9781119992691"},{"article-title":"Is space-time attention all you need for video understanding?","year":"0","author":"bertasius","key":"ref17"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.challengehml-1.3"},{"article-title":"Decoupled weight decay regularization","year":"2017","author":"loshchilov","key":"ref18"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746418"},{"key":"ref25","first-page":"2359","article-title":"Integrating multimodal information in large pre-trained transformers","volume":"2020","author":"rahman","year":"2020","journal-title":"Proceedings of the conference Association for Computational Linguistics Meeting NIH Public Access"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.challengehml-1.1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053012"},{"article-title":"Unsupervised multimodal language representations using convolutional autoencoders","year":"2021","author":"koromilas","key":"ref21"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268987"},{"key":"ref7","article-title":"Unified language model pre-training for natural language understanding and generation","author":"dong","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461718"},{"key":"ref4","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref3","article-title":"Unsupervised mul-timodal language representations using convolutional autoen-coders","author":"zadeh","year":"2018","journal-title":"ACL"},{"key":"ref6","article-title":"Parameter-efficient transfer learning for nlp","author":"houlsby","year":"2019","journal-title":"ICML"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"}],"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\/10094658.pdf?arnumber=10094658","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T13:56:50Z","timestamp":1700488610000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094658\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094658","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}