{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:43:21Z","timestamp":1776883401255,"version":"3.51.2"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100016988","name":"Avignon Universit\u00e9","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100016988","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11433845","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["SENSE models: an open source solution for multilingual and multimodal semantic-based tasks"],"prefix":"10.1109","author":[{"given":"Salima","family":"Mdhaffar","sequence":"first","affiliation":[{"name":"Avignon Université,LIA,Avignon,France"}]},{"given":"Haroun","family":"Elleuch","sequence":"additional","affiliation":[{"name":"Elyadata LIA\/Avignon Université,Tunis,Tunisia"}]},{"given":"Chaimae","family":"Chellaf","sequence":"additional","affiliation":[{"name":"Lundi Matin LIA\/Avignon Université,Avignon,France"}]},{"given":"Ha","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Oracle,France"}]},{"given":"Yannick","family":"Est\u00e8ve","sequence":"additional","affiliation":[{"name":"Avignon Université,LIA,Avignon,France"}]}],"member":"263","reference":[{"key":"ref1","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1835"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383456"},{"key":"ref7","article-title":"mslam: Massively multilingual joint pre-training for speech and text","author":"Bapna","year":"2022","journal-title":"arXiv preprint arXiv:2202.01374"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3192714"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.62"},{"key":"ref11","article-title":"SONAR: sentence-level multimodal and language-agnostic representations","author":"Duquenne","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-08359-z"},{"key":"ref13","article-title":"No language left behind: Scaling human-centered machine translation","author":"Team","year":"2022"},{"issue":"333","key":"ref14","first-page":"1","article-title":"Open-source conversational ai with speechbrain 1.0","volume":"25","author":"Ravanelli","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"ref17","article-title":"Ml-superb: Multilingual speech universal performance benchmark","author":"Yang","year":"2024","journal-title":"ICASSP"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.arabicnlp-1.12"},{"key":"ref19","article-title":"Seamless: Multilingual expressive and streaming speech translation","author":"Barrault","year":"2023","journal-title":"arXiv preprint arXiv:2312.05187"},{"key":"ref20","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Ardila"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref22","article-title":"Attentive pooling networks","author":"Santos","year":"2016","journal-title":"arXiv preprint arXiv:1602.03609"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1202"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-11"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.63317\/2384om53jfnz"},{"key":"ref28","article-title":"Ontonotes release 5.0, 2013","author":"Weischedel"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-957"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.588"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.63317\/4evgpxxgwme5"},{"key":"ref32","article-title":"The spoken language understanding media benchmark dataset in the era of deep learning: data updates, training and evaluation tools","author":"Laperri\u00e8re","year":"2022","journal-title":"LREC 2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023013"},{"key":"ref34","article-title":"End-to-end named entity extraction from speech","author":"Ghannay","year":"2018","journal-title":"SLT"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10231"},{"key":"ref36","first-page":"1343","article-title":"Decoda: a call-centre human-human spoken conversation corpus","volume-title":"Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC\u201912)","author":"Bechet"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2276"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.740"},{"key":"ref39","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref40","article-title":"Bertscore: Evaluating text generation with bert","author":"Zhang","year":"2019","journal-title":"arXiv preprint arXiv:1904.09675"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2027"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00343"},{"key":"ref43","article-title":"Silero vad: pre-trained enterprise-grade voice activity detector (vad), number detector and language classifier","author":"Team","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-78"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11433845.pdf?arnumber=11433845","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:55:11Z","timestamp":1775192111000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11433845\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11433845","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}