{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:57:21Z","timestamp":1764399441157,"version":"3.46.0"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lsp.2025.3627537","type":"journal-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T18:05:56Z","timestamp":1761847556000},"page":"4454-4458","source":"Crossref","is-referenced-by-count":0,"title":["When Voices Speak Louder: Leveraging Audio Signals in Emotion-Cause Extraction via Large Multilingual Multimodal Indian Dialogue Datasets"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4712-3618","authenticated-orcid":false,"given":"Nishant","family":"Kumar","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Patna, Patna, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1043-1296","authenticated-orcid":false,"given":"Srishti","family":"Gupta","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Patna, Patna, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2043-2356","authenticated-orcid":false,"given":"Sourav Kumar","family":"Dandapat","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Patna, Patna, India"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CONIT59222.2023.10205935"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-63776-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122946"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3369726"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3226559"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3446646"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3689646"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3543080"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78128-5_29"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CINS63881.2024.10864457"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.402"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.391"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413909"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i10.7182"},{"article-title":"CPED: A large-scale chinese personalized and emotional dialogue dataset for conversational AI","year":"2022","author":"Chen","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref19","first-page":"3638","article-title":"EmoFilm - A multilingual emotional speech corpus","volume-title":"Proc. Interspeech","author":"Parada-Cabaleiro","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"ref21","first-page":"12111","article-title":"nEMO: Dataset of emotional speech in Polish","volume-title":"Proc. Int. Conf. Lang. Resour. Eval.","author":"Christop","year":"2024"},{"year":"2024","key":"ref22","article-title":"10 most spoken languages in India"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-01221-w"},{"key":"ref24","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3553107"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.611"},{"article-title":"Active learning literature survey","year":"2009","author":"Settles","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2307\/2529310"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111039"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10802935\/11222973.pdf?arnumber=11222973","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:55:38Z","timestamp":1764399338000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11222973\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/lsp.2025.3627537","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2025]]}}}