{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T05:02:20Z","timestamp":1784955740905,"version":"3.55.0"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"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":[[2026,7]]},"DOI":"10.1109\/ecai69016.2026.11613718","type":"proceedings-article","created":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T19:06:59Z","timestamp":1784920019000},"page":"1-13","source":"Crossref","is-referenced-by-count":0,"title":["Automatic Speech Recognition: A Comprehensive Review From HMM-GMM to Self-Supervised Foundation Models"],"prefix":"10.1109","author":[{"given":"Dhiaa M.","family":"Abed","sequence":"first","affiliation":[{"name":"University of Technology","place":["Baghdad, Iraq"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saja B.","family":"Attallah","sequence":"additional","affiliation":[{"name":"University of Technology","place":["Baghdad, Iraq"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Awab Qasim","family":"Karamanji","sequence":"additional","affiliation":[{"name":"University of Technology","place":["Baghdad, Iraq"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruslan S.","family":"Naseef","sequence":"additional","affiliation":[{"name":"University of Technology","place":["Baghdad, Iraq"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hussein M.","family":"Hasan","sequence":"additional","affiliation":[{"name":"University of Technology","place":["Baghdad, Iraq"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abusnina M.","family":"Mukhtar","sequence":"additional","affiliation":[{"name":"Alasmarya Islamic University","place":["Zliten, Libya"],"department":["Department of Biomedical Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali S.","family":"Abdulmohsin","sequence":"additional","affiliation":[{"name":"University of Technology","place":["Baghdad, Iraq"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zaid Ameen","family":"Abduljabbar","sequence":"additional","affiliation":[{"name":"University of Basrah","place":["Basrah, Iraq"],"department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vincent Omollo","family":"Nyangaresi","sequence":"additional","affiliation":[{"name":"Jaramogi Oginga Odinga University of Science & Technology","place":["Bondo, Kenya"],"department":["Department of Computer Science and Software Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/sym11081018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2024.103110"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3550855"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-017-9456-7"},{"key":"ref5","first-page":"1","article-title":"HMM-GMM acoustic modeling for Arabic speech recognition system","volume-title":"International Conference on Mathematics and Data Science","author":"Mait"},{"key":"ref6","first-page":"21","article-title":"Automatic speech recognition","volume-title":"Speech-to-Speech Translation","author":"Lu","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1717\/1\/012009"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2979799"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2896880"},{"key":"ref10","first-page":"150","article-title":"DNN-HMM based automatic speech recognition for HRI scenarios","volume-title":"in: Proc. ACM\/IEEE Int. Conf. Human-Robot Interaction","author":"Novoa"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.06.005"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71928-3_19"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2434"},{"key":"ref14","article-title":"Deep convolutional and LSTM neural networks for acoustic modelling in automatic speech recognition","author":"Liu","year":"2018","journal-title":"Master\u2019s thesis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3020421"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022705"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.iswa.2024.200406"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2970758"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1002\/9781394214624.ch13"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102422"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054224"},{"key":"ref24","first-page":"12449","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 (NeurIPS)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2023.109492"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/app12126223"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.14201\/adcaij.29191"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-756"},{"key":"ref29","article-title":"Multi-resolution HuBERT: Multi-resolution speech self-supervised learning with masked unit prediction","volume-title":"Proc. Int. Conf. Learning Representations (ICLR)","author":"Shi"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-024-00349-3"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1973"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3200910"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3422839"},{"key":"ref34","first-page":"4218","article-title":"Common Voice: A massively-multilingual speech corpus","volume-title":"Proc. Language Resources and Evaluation Conf. (LREC)","author":"Ardila"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2004"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2756440"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3636513"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SAI.2017.8252104"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3390\/app12020903"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3178115"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-024-11614-z"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-026-00458-1"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0680"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/su132212392"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3171967"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1710"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1223"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2112"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3389\/frsip.2022.999457"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101158"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00229"},{"key":"ref52","article-title":"Understanding the role of self-attention for efficient speech recognition","volume-title":"Proc. Int. Conf. Learning Representations (ICLR)","author":"Shim"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2847"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11318"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.32604\/cmes.2022.021755"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-023-10033-0"}],"event":{"name":"2026 18th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)","location":"Bucharest, Romania","start":{"date-parts":[[2026,7,2]]},"end":{"date-parts":[[2026,7,3]]}},"container-title":["2026 18th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11613560\/11613162\/11613718.pdf?arnumber=11613718","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T04:30:21Z","timestamp":1784953821000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11613718\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/ecai69016.2026.11613718","relation":{},"subject":[],"published":{"date-parts":[[2026,7]]}}}