{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:56:52Z","timestamp":1780588612295,"version":"3.54.1"},"reference-count":38,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100010272","name":"Zarqa University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010272","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3550855","type":"journal-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:46:24Z","timestamp":1741801584000},"page":"46925-46940","source":"Crossref","is-referenced-by-count":16,"title":["Advancements in Speech Recognition: A Systematic Review of Deep Learning Transformer Models, Trends, Innovations, and Future Directions"],"prefix":"10.1109","volume":"13","author":[{"given":"Yousef O.","family":"Sharrab","sequence":"first","affiliation":[{"name":"Department of Data Science and Artificial Intelligence, Isra University, Amman, Jordan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8028-7918","authenticated-orcid":false,"given":"Hani","family":"Attar","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Zarqa University, Zarqa, Jordan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1680-2801","authenticated-orcid":false,"given":"Mohammad Ali H.","family":"Eljinini","sequence":"additional","affiliation":[{"name":"Department of Computer Information Systems, Isra University, Amman, Jordan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasmin","family":"Al-Omary","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Jordan University of Science and Technology, Irbid, Jordan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wala\u2019A E.","family":"Al-Momani","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Jordan University of Science and Technology, Irbid, Jordan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Whispy: Adapting STT whisper models to real-time environments","author":"Bevilacqua","year":"2024","journal-title":"arXiv:2405.03484"},{"key":"ref2","article-title":"Deep learning models in speech recognition: Measuring GPU energy consumption, impact of noise and model quantization for edge deployment","author":"Chakravarty","year":"2024","journal-title":"arXiv:2405.01004"},{"key":"ref3","article-title":"Improved contextual recognition in automatic speech recognition systems by semantic lattice rescoring","author":"Sudarshan","year":"2023","journal-title":"arXiv:2310.09680"},{"key":"ref4","article-title":"Neural language model pruning for automatic speech recognition","author":"Emili","year":"2023","journal-title":"arXiv:2310.03424"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-783"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-809"},{"key":"ref7","article-title":"VioLA: Unified codec language models for speech recognition, synthesis, and translation","author":"Wang","year":"2023","journal-title":"arXiv:2305.16107"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1036"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SNAMS58071.2022.10062774"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746639"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688232"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747320"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687871"},{"key":"ref14","article-title":"Effectiveness of self-supervised pre-training for speech recognition","author":"Baevski","year":"2019","journal-title":"arXiv:1911.03912"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747805"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746668"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688079"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053527"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389703"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053213"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414900"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054345"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3383794"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3205753"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389701"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446686"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/eiceeai60672.2023.10590234"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1049\/syb2.12044"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2023.3284056"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IDSTA53674.2021.9660820"},{"key":"ref34","article-title":"A survey on state-of-the-art deep learning applications and challenges","author":"Halim Mohd Noor","year":"2024","journal-title":"arXiv:2403.17561"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1801.01078"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2021.03.088"},{"key":"ref37","first-page":"600","article-title":"CNN-RNN hybrid model to classify local language slangs using spectral features","volume-title":"Proc. Int. Conf. Inventive Comput. Technol. (ICICT)","author":"Ramkumar"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3991\/ijet.v18i02.35997"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10924161.pdf?arnumber=10924161","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T18:41:51Z","timestamp":1742841711000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10924161\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3550855","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}