{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:39:06Z","timestamp":1780501146710,"version":"3.54.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3317236","type":"journal-article","created":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T18:17:23Z","timestamp":1695147443000},"page":"112650-112663","source":"Crossref","is-referenced-by-count":10,"title":["Fine-Tuning Self-Supervised Learning Models for End-to-End Pronunciation Scoring"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9942-0870","authenticated-orcid":false,"given":"Ahmed I.","family":"Zahran","sequence":"first","affiliation":[{"name":"Faculty of Computers and Artificial Intelligence, Cairo University, Giza, Orman, Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aly A.","family":"Fahmy","sequence":"additional","affiliation":[{"name":"Faculty of Computers and Artificial Intelligence, Cairo University, Giza, Orman, Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7401-5219","authenticated-orcid":false,"given":"Khaled T.","family":"Wassif","sequence":"additional","affiliation":[{"name":"Faculty of Computers and Artificial Intelligence, Cairo University, Giza, Orman, Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanaa","family":"Bayomi","sequence":"additional","affiliation":[{"name":"Faculty of Computers and Artificial Intelligence, Cairo University, Giza, Orman, Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607890"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596227"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1997-227"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414451"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-931"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2363"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2953"},{"key":"ref9","article-title":"Vq-wav2vec: Self-supervised learning of discrete speech representations","author":"Baevski","year":"2019","journal-title":"arXiv:1910.05453"},{"key":"ref10","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"arXiv:2006.11477"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.sigmorphon-1.9"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1467"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10245"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9979979"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001493000339"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3328283"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref19","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref20","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016","journal-title":"arXiv:1611.01144"},{"key":"ref21","article-title":"XLM-E: Cross-lingual language model pre-training via ELECTRA","author":"Chi","year":"2021","journal-title":"arXiv:2106.16138"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"issue":"4","key":"ref24","first-page":"35","article-title":"Modern information retrieval: A brief overview","volume":"24","author":"Singhal","year":"2001","journal-title":"IEEE Data Eng. Bull."},{"key":"ref25","article-title":"Professor forcing: A new algorithm for training recurrent networks","volume-title":"Advances in Neural Information Processing Systems","volume":"29","author":"Lamb"},{"key":"ref26","first-page":"577","article-title":"Attention-based models for speech recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Chorowski"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688291"},{"key":"ref29","article-title":"Predicting within and across language phoneme recognition performance of self-supervised learning speech pre-trained models","author":"Ji","year":"2022","journal-title":"arXiv:2206.12489"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9615987"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/s20071809"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.6028\/nist.ir.4930"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1259"},{"key":"ref34","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021","journal-title":"arXiv:2106.04624"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref39","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746743"},{"key":"ref41","article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. IEEE Workshop Autom. Speech Recognit. Understand.","author":"Povey"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.12.008"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref44","volume-title":"Applied Statistics and Probability for Engineers","author":"Montgomery","year":"2010"},{"key":"ref45","volume-title":"NormalizedSquaredEuclideanDistance","year":"2010"},{"key":"ref46","first-page":"213","volume-title":"Pronouncing English: A Stress-Based Approach, With CD-Rom","author":"Teschner","year":"2004"},{"key":"ref47","first-page":"18","volume-title":"Speech and Language Engineering","author":"Rajman","year":"2007"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10255657.pdf?arnumber=10255657","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T03:10:27Z","timestamp":1709349027000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10255657\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3317236","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}