{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:06:24Z","timestamp":1776888384648,"version":"3.51.2"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889257","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Strong Alone, Stronger Together: Synergizing Modality-Binding Foundation Models with Optimal Transport for Non-Verbal Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Orchid Chetia","family":"Phukan","sequence":"first","affiliation":[{"name":"IIIT-Delhi,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohd","family":"Mujtaba Akhtar","sequence":"additional","affiliation":[{"name":"IIIT-Delhi,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Girish","sequence":"additional","affiliation":[{"name":"IIIT-Delhi,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Swarup","family":"Ranjan Behera","sequence":"additional","affiliation":[{"name":"Reliance Jio AICoE,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sishir","family":"Kalita","sequence":"additional","affiliation":[{"name":"Armsoftech.air,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arun Balaji","family":"Buduru","sequence":"additional","affiliation":[{"name":"IIIT-Delhi,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajesh","family":"Sharma","sequence":"additional","affiliation":[{"name":"IIIT-Delhi,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S.R Mahadeva","family":"Prasanna","sequence":"additional","affiliation":[{"name":"IIT-Dharwad,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IAdCC.2013.6514336"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095036"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2024-43"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747870"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076364"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095294"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3360885"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11376"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.160"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref12","article-title":"Languagebind: Extending video-language pretraining to n-modality by language-based semantic alignment","author":"Zhu","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747077"},{"key":"ref16","first-page":"12 449","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 information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-2561"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00062"},{"key":"ref19","first-page":"1793","article-title":"Asvp-esd: A dataset and its benchmark for emotion recognition using both speech and non-speech utterances","volume":"8","author":"Landry","year":"2020","journal-title":"Global Scientific Journals"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2023.103004"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1037\/emo0001048"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889257.pdf?arnumber=10889257","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:08Z","timestamp":1774416128000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889257\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889257","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}