{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:36:01Z","timestamp":1753601761246,"version":"3.37.3"},"reference-count":62,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T00:00:00Z","timestamp":1700524800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T00:00:00Z","timestamp":1700524800000},"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":[[2023,11,21]]},"DOI":"10.1109\/snams60348.2023.10375468","type":"proceedings-article","created":{"date-parts":[[2024,1,2]],"date-time":"2024-01-02T20:36:22Z","timestamp":1704227782000},"page":"1-9","source":"Crossref","is-referenced-by-count":1,"title":["Breaking Barriers: Can Multilingual Foundation Models Bridge the Gap in Cross-Language Speech Emotion Recognition?"],"prefix":"10.1109","author":[{"given":"Moazzam","family":"Shoukat","sequence":"first","affiliation":[{"name":"EmulationAI,Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad","family":"Usama","sequence":"additional","affiliation":[{"name":"National University of Computer & Emerging Sciences,Faisalabad,Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hafiz Shehbaz","family":"Ali","sequence":"additional","affiliation":[{"name":"EmulationAI,Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5662-4777","authenticated-orcid":false,"given":"Siddique","family":"Latif","sequence":"additional","affiliation":[{"name":"University of Southern Queensland (UniSQ) Queensland University of Technology (QUT),Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3114365"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/FIT.2018.00023"},{"key":"ref4","article-title":"Deep representation learning for speech emotion recognition","volume-title":"University of Southern Queensland","author":"Latif","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11277-023-10244-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2936124"},{"key":"ref7","article-title":"A survey of code-switched speech and language processing","author":"Sitaram","year":"2019","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/s22072461"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.01.002"},{"key":"ref11","article-title":"Ai-based emotion recognition: Promise, peril, and prescriptions for prosocial path","author":"Latif","year":"2022","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Seamlessm4t-massively multilingual & multimodal machine translation","author":"Barrault","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"A comprehensive survey on pretrained foundation models: A history from bert to chatgpt","author":"Zhou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Sparks of large audio models: A survey and outlook","author":"Latif","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Can large language models aid in annotating speech emotional data? uncovering new frontiers","author":"Latif","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"12 449","article-title":"wav2vec 2.0: A frame-work for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","article-title":"Un-supervised cross-lingual representation learning for speech recognition","author":"Conneau","year":"2020","journal-title":"arXiv preprint"},{"key":"ref19","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning. PMLR","author":"Radford"},{"key":"ref20","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3548457"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i10.7158"},{"key":"ref23","article-title":"A very low resource language speech corpus for computational language documentation experiments","author":"Godard","year":"2017","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2018.11.028"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.03.002"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2019.8925513"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/s22176445"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3190"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2561"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2019EDL8136"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3131"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref35","article-title":"Meld: A multimodal multi-party dataset for emotion recognition in conversations","author":"Poria","year":"2018","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Mosi: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos","author":"Zadeh","year":"2016","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Transformers in speech processing: A survey","author":"Latif","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746598"},{"volume-title":"Transformer-cnn emotion recognition","year":"2021","author":"Zenkov","key":"ref39"},{"key":"ref40","first-page":"1","article-title":"Speech emotion recognition transformer: A novel end-to-end model for ser","volume":"454","author":"Li","year":"2021","journal-title":"Neurocomputing"},{"key":"ref41","first-page":"112","article-title":"Msp-podcast: A large-scale dataset of natural and emotionally evocative speech","volume-title":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","author":"Park"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10371"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105907"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2021.697634"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.02.006"},{"key":"ref46","first-page":"101122","article-title":"Multi-head attention fusion networks for multi-modal speech emotion recognition","volume":"65","author":"Ho","year":"2020","journal-title":"Computer Speech & Language"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747870"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3193288"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639583"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1570"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683765"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2916092"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3221749"},{"key":"ref56","article-title":"Peft-ser: On the use of parameter efficient transfer learning approaches for speech emotion recognition using pre-trained speech models","author":"Feng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3194"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1718"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"},{"key":"ref61","first-page":"3501","article-title":"Emovo corpus: an italian emotional speech database","volume-title":"Proceedings of the ninth international conference on language resources and evaluation (LREC14)","author":"Costantini"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"}],"event":{"name":"2023 Tenth International Conference on Social Networks Analysis, Management and Security (SNAMS)","start":{"date-parts":[[2023,11,21]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2023,11,24]]}},"container-title":["2023 Tenth International Conference on Social Networks Analysis, Management and Security (SNAMS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10375374\/10375393\/10375468.pdf?arnumber=10375468","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T22:26:42Z","timestamp":1705098402000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10375468\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,21]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/snams60348.2023.10375468","relation":{},"subject":[],"published":{"date-parts":[[2023,11,21]]}}}