{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T22:19:44Z","timestamp":1793485184464,"version":"4.5.0"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T00:00:00Z","timestamp":1746489600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["MethodsX"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1016\/j.mex.2025.103359","type":"journal-article","created":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T03:05:50Z","timestamp":1746587150000},"page":"103359","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":14,"special_numbering":"C","title":["Bridging language gaps: The role of NLP and speech recognition in oral english instruction"],"prefix":"10.1016","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8903-6664","authenticated-orcid":false,"given":"Parul","family":"Dubey","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pushkar","family":"Dubey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rohit","family":"Raja","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sapna Singh","family":"Kshatri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.mex.2025.103359_bib0001","doi-asserted-by":"crossref","unstructured":"X. Pan, P. Chen, Y. Gong, H. Zhou, X. Wang, and Z. Lin, \u201cLeveraging unimodal self-supervised learning for multimodal audio-visual speech recognition,\u201d arxiv (Cornell University), 2022, doi:10.48550\/arxiv.2203.07996.","DOI":"10.18653\/v1\/2022.acl-long.308"},{"key":"10.1016\/j.mex.2025.103359_bib0002","doi-asserted-by":"crossref","unstructured":"S. Padi, S.O. Sadjadi, D. Manocha, and R.D. Sriram, \u201cMultimodal emotion recognition using transfer learning from Speaker recognition and BERT-based models,\u201d arxiv (Cornell University), 2022, doi:10.48550\/arxiv.2202.08974.","DOI":"10.21437\/Odyssey.2022-57"},{"issue":"6","key":"10.1016\/j.mex.2025.103359_bib0003","doi-asserted-by":"crossref","first-page":"887","DOI":"10.3390\/healthcare11060887","article-title":"ChatGPT utility in Healthcare education, research, and practice: systematic review on the promising perspectives and valid concerns","volume":"11","author":"Sallam","year":"2023","journal-title":"Healthcare"},{"key":"10.1016\/j.mex.2025.103359_bib0004","doi-asserted-by":"crossref","unstructured":"M. Sunkara, S. Ronanki, D. Bekal, S. Bodapati, and K. Kirchhoff, \u201cMultimodal semi-supervised learning framework for punctuation prediction in conversational speech,\u201d arxiv (Cornell University), 2020, doi:10.48550\/arxiv.2008.00702.","DOI":"10.21437\/Interspeech.2020-3074"},{"key":"10.1016\/j.mex.2025.103359_bib0005","series-title":"Proceedings of the Companion Publication of the 2020 International Conference on Multimodal Interaction","article-title":"Speech emotion recognition among elderly individuals using multimodal fusion and transfer learning","author":"Boateng","year":"2020"},{"key":"10.1016\/j.mex.2025.103359_bib0006","doi-asserted-by":"crossref","unstructured":"Z. Zhao, Y. Wang, and Y. Wang, \u201cMulti-level fusion of Wav2vec 2.0 and BERT for multimodal emotion recognition,\u201d arxiv (Cornell University), 2022, doi:10.48550\/arxiv.2207.04697.","DOI":"10.21437\/Interspeech.2022-10230"},{"key":"10.1016\/j.mex.2025.103359_bib0007","doi-asserted-by":"crossref","unstructured":"Z. Liu, S.X. Yin, C. Lee, and N.F. Chen, \u201cScaffolding language learning via multi-modal tutoring systems with pedagogical instructions,\u201d arxiv (Cornell University), 2024, doi:10.48550\/arxiv.2404.03429.","DOI":"10.1109\/CAI59869.2024.00223"},{"key":"10.1016\/j.mex.2025.103359_bib0008","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.aej.2024.10.065","article-title":"Transforming English language learning: advanced speech recognition with MLP-LSTM for personalized education","volume":"111","author":"Orosoo","year":"2024","journal-title":"Alex. Eng. J."},{"key":"10.1016\/j.mex.2025.103359_bib0009","article-title":"Influencing factors on NLP technology integration in teaching: a case study in Shanghai","author":"Lyu","year":"2024","journal-title":"Educ. Inf. Technol."},{"issue":"1","key":"10.1016\/j.mex.2025.103359_bib0010","doi-asserted-by":"crossref","DOI":"10.1080\/2331186X.2024.2404264","article-title":"Formation of auditory and speech competences in learning English based on neural network technologies: psycholinguistic aspect","volume":"11","author":"Mirzoyeva","year":"2024","journal-title":"Cogent Educ."},{"key":"10.1016\/j.mex.2025.103359_bib0011","doi-asserted-by":"crossref","unstructured":"W. Xiaoyu, Virtual communication partner for english learning based on speech recognition. 2024, pp. 365\u2013368. doi:10.1109\/ecei60433.2024.10510812.","DOI":"10.1109\/ECEI60433.2024.10510812"},{"key":"10.1016\/j.mex.2025.103359_bib0012","doi-asserted-by":"crossref","unstructured":"D. Litman, \u201cSpeech and language processing for adaptive training,\u201d in Cambridge University Press eBooks, 2012, pp. 247\u2013260. doi:10.1017\/cbo9781139049580.019.","DOI":"10.1017\/CBO9781139049580.019"},{"key":"10.1016\/j.mex.2025.103359_bib0013","doi-asserted-by":"crossref","unstructured":"K. Kandji, C. Ba, and S. Ndiaye, State-of-the-art review on recent trends in automatic speech recognition. 2024, pp. 185\u2013203. doi:10.1007\/978-3-031-63999-9_11.","DOI":"10.1007\/978-3-031-63999-9_11"},{"key":"10.1016\/j.mex.2025.103359_bib0014","series-title":"Integrated Digital Language Learning","first-page":"89","author":"Antoniadis","year":"2009"},{"issue":"3","key":"10.1016\/j.mex.2025.103359_bib0015","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1109\/JSTSP.2020.2989852","article-title":"Introduction to the special issue on deep learning for multi-modal intelligence across speech, language, vision, and heterogeneous signals","volume":"14","author":"He","year":"2020","journal-title":"IEEE J. Sel. Top. Signal. Process."},{"key":"10.1016\/j.mex.2025.103359_bib0016","series-title":"Proceedings of the 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","article-title":"Multimodal emotion recognition with high-level speech and text features","author":"Makiuchi","year":"2021"},{"key":"10.1016\/j.mex.2025.103359_bib0017","unstructured":"Ghaleb et al., \u201cLeveraging speech for gesture detection in multimodal communication,\u201d arxiv (Cornell University), 2024, doi:10.48550\/arxiv.2404.14952."},{"key":"10.1016\/j.mex.2025.103359_bib0018","doi-asserted-by":"crossref","DOI":"10.3389\/fnbot.2023.1181598","article-title":"Multimodal transformer augmented fusion for speech emotion recognition","volume":"17","author":"Wang","year":"2023","journal-title":"Front. Neurorobotics"},{"key":"10.1016\/j.mex.2025.103359_bib0019","doi-asserted-by":"crossref","unstructured":"P. Dighe et al., \u201cLeveraging large language models for exploiting ASR uncertainty,\u201d 2024, doi:10.1109\/icassp48485.2024.10446132.","DOI":"10.1109\/ICASSP48485.2024.10446132"},{"issue":"3","key":"10.1016\/j.mex.2025.103359_bib0020","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1109\/JSTSP.2020.2987728","article-title":"Multimodal intelligence: representation learning, information fusion, and applications","volume":"14","author":"Zhang","year":"2020","journal-title":"IEEE J. Sel. Top. Signal. Process."},{"key":"10.1016\/j.mex.2025.103359_bib0021","doi-asserted-by":"crossref","unstructured":"Z. Chen et al., \u201cSALM: speech-augmented language model with in-context learning for speech recognition and translation,\u201d 2024, doi:10.1109\/icassp48485.2024.10447553.","DOI":"10.1109\/ICASSP48485.2024.10447553"},{"key":"10.1016\/j.mex.2025.103359_bib0022","doi-asserted-by":"crossref","unstructured":"S. Sharma, M. Vashisht, and V. Kumar, \u201cEnhanced customer insights: multimodal NLP feedback system,\u201d 2024, doi:10.1109\/sceecs61402.2024.10481937.","DOI":"10.1109\/SCEECS61402.2024.10481937"},{"key":"10.1016\/j.mex.2025.103359_bib0023","doi-asserted-by":"crossref","unstructured":"Y. Wu, Z. Zhang, P. Peng, Y. Zhao, and B. Qin, \u201cLeveraging multi-modal interactions among the intermediate representations of deep transformers for emotion recognition,\u201d 2022, doi:10.1145\/3551876.3554813.","DOI":"10.1145\/3551876.3554813"},{"key":"10.1016\/j.mex.2025.103359_bib0024","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.neunet.2020.06.015","article-title":"Heart sound classification based on improved MFCC features and convolutional recurrent neural networks","volume":"130","author":"Deng","year":"2020","journal-title":"Neural Netw."},{"key":"10.1016\/j.mex.2025.103359_bib0025","doi-asserted-by":"crossref","first-page":"122136","DOI":"10.1109\/ACCESS.2022.3223444","article-title":"Mel frequency cepstral coefficient and its applications: a review","volume":"10","author":"Kh. Abdul","year":"2022","journal-title":"IEEE Access."},{"issue":"2","key":"10.1016\/j.mex.2025.103359_bib0026","doi-asserted-by":"crossref","DOI":"10.1007\/s42979-020-0093-x","article-title":"Isolated command recognition using MFCC and clustering algorithm","volume":"1","author":"Revathi","year":"2020","journal-title":"SN Comput. Sci."},{"key":"10.1016\/j.mex.2025.103359_bib0027","doi-asserted-by":"crossref","unstructured":"T. Srinivasan, R. Sanabria, F. Metze, and D. Elliott, \u201cFine-grained grounding for multimodal speech recognition,\u201d arxiv (Cornell University),2020, doi:10.48550\/arxiv.2010.02384.","DOI":"10.18653\/v1\/2020.findings-emnlp.242"},{"key":"10.1016\/j.mex.2025.103359_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.compeleceng.2020.106943","article-title":"Multimodal speech recognition for unmanned aerial vehicles","volume":"90","author":"Onea\u021b\u0103","year":"2021","journal-title":"Comput. Electr. Eng."},{"key":"10.1016\/j.mex.2025.103359_bib0029","doi-asserted-by":"crossref","first-page":"176274","DOI":"10.1109\/ACCESS.2020.3026823","article-title":"Multimodal emotion recognition with transformer-based self supervised feature fusion","volume":"8","author":"Siriwardhana","year":"2020","journal-title":"IEEe Access."},{"key":"10.1016\/j.mex.2025.103359_bib0030","first-page":"1","article-title":"Gaussian inflection point selection for LiDAR hidden echo signal decomposition","volume":"19","author":"Zhou","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.mex.2025.103359_bib0031","doi-asserted-by":"crossref","unstructured":"B. Sharma, M. Madhavi, and H. Li, \u201cLeveraging acoustic and linguistic embeddings from pretrained speech and language models for intent classification,\u201d 2021, doi:10.1109\/icassp39728.2021.9413388.","DOI":"10.1109\/ICASSP39728.2021.9413388"},{"key":"10.1016\/j.mex.2025.103359_bib0032","series-title":"Proceedings of the 37th ACM\/SIGAPP Symposium on Applied Computing","article-title":"Leveraging multimodal content for podcast summarization","author":"Vaiani","year":"2022"},{"key":"10.1016\/j.mex.2025.103359_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.ymssp.2021.107760","article-title":"Sampling methods for solving bayesian model updating problems: a tutorial","volume":"159","author":"Lye","year":"2021","journal-title":"Mech. Syst. Signal. Process."},{"issue":"6","key":"10.1016\/j.mex.2025.103359_bib0034","doi-asserted-by":"crossref","first-page":"411","DOI":"10.17762\/ijritcc.v11i6.7734","article-title":"An efficient probabilistic deep learning model for the oral proficiency assessment of student speech recognition and classification","volume":"11","author":"Li","year":"2023","journal-title":"Int. J. Recent Innov. Trends Comput. Commun."},{"issue":"2","key":"10.1016\/j.mex.2025.103359_bib0035","doi-asserted-by":"crossref","first-page":"709","DOI":"10.12694\/scpe.v25i2.2544","article-title":"Research on speech communication enhancement of English web-based learning platform based on Human-computer intelligent interaction","volume":"25","author":"Gu","year":"2024","journal-title":"Scalable Comput. Pract. Exp."},{"key":"10.1016\/j.mex.2025.103359_bib0036","doi-asserted-by":"crossref","DOI":"10.3389\/fnbot.2024.1478181","article-title":"Multimodal fusion-powered English speaking robot","volume":"18","author":"Pan","year":"2024","journal-title":"Front. Neurorobotics"},{"key":"10.1016\/j.mex.2025.103359_bib0037","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.aej.2024.10.065","article-title":"Transforming English language learning: advanced speech recognition with MLP-LSTM for personalized education","volume":"111","author":"Orosoo","year":"2024","journal-title":"Alex. Eng. J."},{"issue":"2","key":"10.1016\/j.mex.2025.103359_bib0038","first-page":"3513","article-title":"Artificial intelligence speech recognition model for correcting spoken English teaching","volume":"40","author":"Ran","year":"2020","journal-title":"J. Intell. Fuzzy Syst."},{"key":"10.1016\/j.mex.2025.103359_bib0039","doi-asserted-by":"crossref","first-page":"1410","DOI":"10.1007\/978-3-031-37717-4_93","article-title":"The effect of ASR apps on monophthong pronunciation improvement and generalization to new words in English","author":"Xiao","year":"2023","journal-title":"Lect. Notes Netw. Syst."},{"key":"10.1016\/j.mex.2025.103359_bib0040","series-title":"Automatic Speech Recognition to Enhance Learning for Disabled Students","first-page":"478","author":"Revuelta","year":"2013"},{"issue":"3","key":"10.1016\/j.mex.2025.103359_bib0041","doi-asserted-by":"crossref","first-page":"424","DOI":"10.1093\/jdsade\/enae019","article-title":"Deaf\/hard of hearing students\u2019 experiences with higher education\u2019s real-time captioning services","volume":"29","author":"Jolly","year":"2024","journal-title":"J. Deaf Stud. Deaf Educ."},{"key":"10.1016\/j.mex.2025.103359_bib0042","series-title":"Speaker Recognition - CMU ARCTIC","year":"2022"},{"key":"10.1016\/j.mex.2025.103359_bib0043","series-title":"LibriSpeech ASR corpus","year":"2023"}],"container-title":["MethodsX"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2215016125002055?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2215016125002055?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T16:54:55Z","timestamp":1771865695000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2215016125002055"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":43,"alternative-id":["S2215016125002055"],"URL":"https:\/\/doi.org\/10.1016\/j.mex.2025.103359","relation":{},"ISSN":["2215-0161"],"issn-type":[{"value":"2215-0161","type":"print"}],"subject":[],"published":{"date-parts":[[2025,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Bridging language gaps: The role of NLP and speech recognition in oral english instruction","name":"articletitle","label":"Article Title"},{"value":"MethodsX","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.mex.2025.103359","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"103359"}}