{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:32:17Z","timestamp":1775068337743,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249284","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"636-641","source":"Crossref","is-referenced-by-count":1,"title":["Are Multimodal Foundation Models All That Is Needed for Emofake Detection?"],"prefix":"10.1109","author":[{"given":"Mohd Mujtaba","family":"Akhtar","sequence":"first","affiliation":[{"name":"V.B.S.P.U,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Girish","sequence":"additional","affiliation":[{"name":"IIIT-Delhi,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Orchid Chetia","family":"Phukan","sequence":"additional","affiliation":[{"name":"IIIT-Delhi,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Swarup Ranjan","family":"Behera","sequence":"additional","affiliation":[{"name":"Independent Researcher,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pailla Balakrishna","family":"Reddy","sequence":"additional","affiliation":[{"name":"Reliance AI,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ananda Chandra","family":"Nayak","sequence":"additional","affiliation":[{"name":"KAC,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanjib Kumar","family":"Nayak","sequence":"additional","affiliation":[{"name":"VSSUT,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arun Balaji","family":"Buduru","sequence":"additional","affiliation":[{"name":"IIIT-Delhi,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110468"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448184"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2694139"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-481"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832226"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447923"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-1302"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446560"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1537"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.227"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-1185"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-8367-0_25"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.160"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC58517.2023.10317508"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747077"},{"key":"ref17","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural infor-mation processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref20","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1537"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10887871"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref24","article-title":"Languagebind: Extending video-language pretraining to n -modality by language-based semantic alignment","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-2561"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC58517.2023.10317562"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Singapore, Singapore","start":{"date-parts":[[2025,10,22]]},"end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249284.pdf?arnumber=11249284","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:24:00Z","timestamp":1764401040000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249284\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249284","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}