{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T21:45:15Z","timestamp":1780955115215,"version":"3.54.1"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Deputyship for Research & Innovation, \u201cMinistry of Education\u201d in Saudi Arabia for funding this research"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3339537","type":"journal-article","created":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T18:25:42Z","timestamp":1701800742000},"page":"140967-140980","source":"Crossref","is-referenced-by-count":3,"title":["SBVQA 2.0: Robust End-to-End Speech-Based Visual Question Answering for Open-Ended Questions"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5025-4020","authenticated-orcid":false,"given":"Faris","family":"Alasmary","sequence":"first","affiliation":[{"name":"Department of Computer Science, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9406-6809","authenticated-orcid":false,"given":"Saad","family":"Al-Ahmadi","sequence":"additional","affiliation":[{"name":"Department of Computer Science, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICITA.2005.78"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1805986.1806020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref5","article-title":"Speech-based visual question answering","author":"Zhang","year":"2017","journal-title":"arXiv:1705.00464"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.153"},{"key":"ref7","first-page":"9617","article-title":"TVLT: Textless vision-language transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Tang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref9","volume-title":"Why is speech recognition difficult?","author":"Forsberg","year":"2003"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref13","first-page":"10937","article-title":"UniSpeech: Unified speech representation learning with labeled and unlabeled data","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Wang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"ref17","author":"Harper","year":"2023","journal-title":"NeMo: A Toolkit for Conversational AI and Large Language Models"},{"key":"ref18","article-title":"How do vision transformers work?","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Park"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref23","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Li"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66709-6_5"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00886"},{"key":"ref27","first-page":"1","article-title":"An image is worth 16 \u2717 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref30","first-page":"208","article-title":"Effects of layer freezing on transferring a speech recognition system to under-resourced languages","volume-title":"Proc. 17th Conf. Natural Lang. Process. (KONVENS)","author":"Eberhard"},{"key":"ref31","article-title":"Deep ViT features as dense visual descriptors","author":"Amir","year":"2021","journal-title":"arXiv:2112.05814"},{"key":"ref32","first-page":"12116","article-title":"Do vision transformers see like convolutional neural networks?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Raghu"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.97.2.285"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10343139.pdf?arnumber=10343139","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T01:47:50Z","timestamp":1705024070000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10343139\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3339537","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}