{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T07:56:19Z","timestamp":1777276579937,"version":"3.51.4"},"reference-count":22,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T00:00:00Z","timestamp":1754265600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers and Education: Artificial Intelligence"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1016\/j.caeai.2025.100458","type":"journal-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T23:19:39Z","timestamp":1754522379000},"page":"100458","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["English listening and speaking ability evaluation model fusing computer vision and speech recognition algorithms"],"prefix":"10.1016","volume":"9","author":[{"given":"Yihui","family":"Zeng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.caeai.2025.100458_bib1","doi-asserted-by":"crossref","first-page":"51","DOI":"10.3390\/technologies9030051","article-title":"Behavioral pattern analysis between bilingual and monolingual listeners' natural speech perception on foreign-accented English language using different machine learning approaches","volume":"9","author":"Ahad","year":"2021","journal-title":"Technologies"},{"issue":"2","key":"10.1016\/j.caeai.2025.100458_bib2","doi-asserted-by":"crossref","first-page":"5547","DOI":"10.48084\/etasr.3465","article-title":"Efficient feature extraction algorithms to develop an Arabic speech recognition system","volume":"10","author":"Alasadi","year":"2020","journal-title":"Engineering, Technology & Applied Science Research"},{"issue":"7","key":"10.1016\/j.caeai.2025.100458_bib3","doi-asserted-by":"crossref","first-page":"2648","DOI":"10.1044\/2022_JSLHR-21-00667","article-title":"Identifying language disorder in bilingual children using automatic speech recognition","volume":"65","author":"Albudoor","year":"2022","journal-title":"Journal of Speech, Language, and Hearing Research"},{"issue":"8","key":"10.1016\/j.caeai.2025.100458_bib4","doi-asserted-by":"crossref","first-page":"1869","DOI":"10.1080\/09588221.2020.1839504","article-title":"Effects of an automatic speech recognition system with peer feedback on pronunciation instruction for adults","volume":"35","author":"Evers","year":"2022","journal-title":"Computer Assisted Language Learning"},{"issue":"4","key":"10.1016\/j.caeai.2025.100458_bib5","first-page":"7085","article-title":"Quality evaluation of English pronunciation based on artificial emotion recognition and Gaussian mixture model","volume":"40","author":"Gang","year":"2021","journal-title":"Journal of Intelligent and Fuzzy Systems"},{"issue":"1","key":"10.1016\/j.caeai.2025.100458_bib6","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1080\/15434303.2023.2283839","article-title":"What do the measures of utterance fluency employed in automatic speech evaluation (ASE) tell Us about oral proficiency?","volume":"21","author":"Handley","year":"2024","journal-title":"Language Assessment Quarterly"},{"issue":"1","key":"10.1016\/j.caeai.2025.100458_bib7","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1017\/S0958344022000192","article-title":"Assessment of L2 intelligibility: Comparing L1 listeners and automatic speech recognition","volume":"35","author":"Inceoglu","year":"2023","journal-title":"ReCALL"},{"issue":"2","key":"10.1016\/j.caeai.2025.100458_bib8","doi-asserted-by":"crossref","first-page":"110","DOI":"10.14742\/ajet.6798","article-title":"Using automatic speech recognition technology to enhance EFL learners' oral language complexity in a flipped classroom","volume":"37","author":"Jiang","year":"2021","journal-title":"Australasian Journal of Educational Technology"},{"issue":"2","key":"10.1016\/j.caeai.2025.100458_bib9","first-page":"219","article-title":"Automatic speech recognition in computer-assisted language learning for individual learning in speaking","volume":"5","author":"Junining","year":"2020","journal-title":"Journal of English Educators Society"},{"issue":"2","key":"10.1016\/j.caeai.2025.100458_bib10","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.ijcce.2022.01.003","article-title":"Deep learning based assistive technology on audio visual speech recognition for hearing impaired","volume":"3","author":"Kumar","year":"2022","journal-title":"International Journal of Cognitive Computing in Engineering"},{"issue":"2","key":"10.1016\/j.caeai.2025.100458_bib11","first-page":"2433","article-title":"Design of English text-to-speech conversion algorithm based on machine learning","volume":"40","author":"Li","year":"2021","journal-title":"Journal of Intelligent and Fuzzy Systems"},{"issue":"8","key":"10.1016\/j.caeai.2025.100458_bib12","doi-asserted-by":"crossref","first-page":"3608","DOI":"10.1109\/TNNLS.2020.3015830","article-title":"A unified framework for multilingual speech recognition in air traffic control systems","volume":"32","author":"Lin","year":"2020","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"9s","key":"10.1016\/j.caeai.2025.100458_bib13","first-page":"484","article-title":"Optimizing speech recognition and evaluation models in English listening training using machine learning algorithms","volume":"20","author":"Liu","year":"2024","journal-title":"Journal of Electrical Systems"},{"issue":"2","key":"10.1016\/j.caeai.2025.100458_bib14","first-page":"3513","article-title":"Artificial intelligence speech recognition model for correcting spoken English teaching","volume":"40","author":"Ran","year":"2021","journal-title":"Journal of Intelligent and Fuzzy Systems"},{"issue":"2","key":"10.1016\/j.caeai.2025.100458_bib15","doi-asserted-by":"crossref","first-page":"93","DOI":"10.16875\/stem.2021.22.2.93","article-title":"Assessing the practicality of using an automatic speech recognition tool to teach English pronunciation online","volume":"22","author":"Spring","year":"2021","journal-title":"Journal of English Teaching through Movies and Media"},{"issue":"3","key":"10.1016\/j.caeai.2025.100458_bib16","doi-asserted-by":"crossref","first-page":"546","DOI":"10.14569\/IJACSA.2021.0120365","article-title":"Recent advancement in speech recognition for bangla: A survey","volume":"12","author":"Sultana","year":"2021","journal-title":"International Journal of Advanced Computer Science and Applications"},{"issue":"1","key":"10.1016\/j.caeai.2025.100458_bib17","first-page":"5575541","article-title":"Research on business English translation framework based on speech recognition and wireless communication","volume":"2021","author":"Wu","year":"2021","journal-title":"Mobile Information Systems"},{"issue":"1","key":"10.1016\/j.caeai.2025.100458_bib18","first-page":"7186375","article-title":"English speech recognition and evaluation of pronunciation quality using deep learning","volume":"2022","author":"Xu","year":"2022","journal-title":"Mobile Information Systems"},{"issue":"4","key":"10.1016\/j.caeai.2025.100458_bib19","doi-asserted-by":"crossref","first-page":"19","DOI":"10.13064\/KSSS.2020.12.4.019","article-title":"An evaluation of Korean students' pronunciation of an English passage by a speech recognition application and two human raters","volume":"12","author":"Yang","year":"2020","journal-title":"Phonetics and Speech Sciences"},{"issue":"3","key":"10.1016\/j.caeai.2025.100458_bib20","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1007\/s10772-020-09733-8","article-title":"English speech sound improvement system based on deep learning from signal processing to semantic recognition","volume":"23","author":"Yang","year":"2020","journal-title":"International Journal of Speech Technology"},{"issue":"36","key":"10.1016\/j.caeai.2025.100458_bib21","doi-asserted-by":"crossref","first-page":"24961","DOI":"10.1007\/s00521-023-08462-8","article-title":"Exploration of English speech translation recognition based on the LSTM RNN algorithm","volume":"35","author":"Yuan","year":"2023","journal-title":"Neural Computing & Applications"},{"issue":"3","key":"10.1016\/j.caeai.2025.100458_bib22","doi-asserted-by":"crossref","first-page":"1037","DOI":"10.52783\/jes.3431","article-title":"Using speech recognition algorithms to improve listening training effects in foreign","volume":"20","author":"Zhang","year":"2024","journal-title":"Journal of Electrical Systems"}],"container-title":["Computers and Education: Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666920X25000980?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666920X25000980?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T07:13:14Z","timestamp":1777273994000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2666920X25000980"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":22,"alternative-id":["S2666920X25000980"],"URL":"https:\/\/doi.org\/10.1016\/j.caeai.2025.100458","relation":{},"ISSN":["2666-920X"],"issn-type":[{"value":"2666-920X","type":"print"}],"subject":[],"published":{"date-parts":[[2025,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"English listening and speaking ability evaluation model fusing computer vision and speech recognition algorithms","name":"articletitle","label":"Article Title"},{"value":"Computers and Education: Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.caeai.2025.100458","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Author. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"100458"}}