{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T16:30:33Z","timestamp":1792686633801,"version":"4.5.0"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T00:00:00Z","timestamp":1730851200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T00:00:00Z","timestamp":1730851200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-024-78557-2","type":"journal-article","created":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T16:02:22Z","timestamp":1730908942000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Speech recognition using an english multimodal corpus with integrated image and depth information"],"prefix":"10.1038","volume":"14","author":[{"given":"Bing","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,6]]},"reference":[{"key":"78557_CR1","doi-asserted-by":"crossref","unstructured":"Xu, J. & Li, T. Application of multimodal NLP instruction combined with speech recognition in oral english practice. Mobile Inform. Syst.  1 (2022)  2262696. (2022).","DOI":"10.1155\/2022\/2262696"},{"issue":"8","key":"78557_CR2","doi-asserted-by":"publisher","first-page":"3608","DOI":"10.1109\/TNNLS.2020.3015830","volume":"32","author":"Y Lin","year":"2020","unstructured":"Lin, Y. A unified framework for multilingual speech recognition in air traffic control systems. IEEE Trans. Neural Netw. Learn. Syst. 32 (8), 3608\u20133620 (2020).","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"78557_CR3","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1109\/TASLP.2022.3224305","volume":"31","author":"M Wang","year":"2022","unstructured":"Wang, M., Chen, J., Zhang, X. L. & Rahardja, S. End-to-end multi-modal speech recognition on an air and bone conducted speech corpus. IEEE\/ACM Trans. Audio Speech Lang. Process. 31, 513\u2013524 (2022).","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"3","key":"78557_CR4","first-page":"80","volume":"10","author":"S Benkerzaz","year":"2019","unstructured":"Benkerzaz, S., Elmir, Y. & Dennai, A. A study on automatic speech recognition. J. Inform. Technol. Rev. 10 (3), 80\u201383 (2019).","journal-title":"J. Inform. Technol. Rev."},{"issue":"5","key":"78557_CR5","doi-asserted-by":"publisher","first-page":"3673","DOI":"10.1007\/s10462-019-09775-8","volume":"53","author":"A Singh","year":"2020","unstructured":"Singh, A. ASRoIL: a comprehensive survey for automatic speech recognition of Indian languages. Artif. Intell. Rev. 53 (5), 3673\u20133704 (2020).","journal-title":"Artif. Intell. Rev."},{"issue":"2","key":"78557_CR6","doi-asserted-by":"publisher","first-page":"3513","DOI":"10.3233\/JIFS-189388","volume":"40","author":"D Ran","year":"2021","unstructured":"Ran, D., Yingli, W. & Haoxin, Q. Artificial intelligence speech recognition model for correcting spoken English teaching. J. Intell. Fuzzy Syst. 40 (2), 3513\u20133524 (2021).","journal-title":"J. Intell. Fuzzy Syst."},{"issue":"3","key":"78557_CR7","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1007\/s11831-020-09414-4","volume":"28","author":"J Kaur","year":"2021","unstructured":"Kaur, J., Singh, A. & Kadyan, V. Automatic speech recognition system for tonal languages: state-of-the-art survey. Arch. Comput. Methods Eng. 28 (3), 1039\u20131068 (2021).","journal-title":"Arch. Comput. Methods Eng."},{"issue":"1","key":"78557_CR8","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1093\/llc\/fqz080","volume":"36","author":"L Huang","year":"2021","unstructured":"Huang, L. Toward multimodal corpus pragmatics: Rationale, case, and agenda. Digit. Scholarsh. Humanit. 36 (1), 101\u2013114 (2021).","journal-title":"Digit. Scholarsh. Humanit."},{"issue":"3","key":"78557_CR9","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1007\/s10579-020-09517-1","volume":"55","author":"T Hiippala","year":"2021","unstructured":"Hiippala, T. AI2D-RST: a multimodal corpus of 1000 primary school science diagrams. Lang. Resour. Eval. 55 (3), 661\u2013688 (2021).","journal-title":"Lang. Resour. Evaluation"},{"issue":"4","key":"78557_CR10","doi-asserted-by":"publisher","first-page":"1077","DOI":"10.1007\/s10579-020-09526-0","volume":"55","author":"M Snaith","year":"2021","unstructured":"Snaith, M. A multimodal corpus of simulated consultations between a patient and multiple healthcare professionals. Lang. Resour. Eval.  55 (4), 1077\u20131092 (2021).","journal-title":"Lang. Resour. Evaluation"},{"key":"78557_CR11","doi-asserted-by":"crossref","unstructured":"Tian, M. Construction of computer English corpus assisted by internet of things information perception and interaction technology. Comput. Intell. Neurosci.  1 (2022)  6803802. (2022).","DOI":"10.1155\/2022\/6803802"},{"issue":"5","key":"78557_CR12","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1007\/s10579-020-09517-1","volume":"5","author":"T Hiippala","year":"2021","unstructured":"Hiippala, T. et al. AI2D-RST: a multimodal corpus of 1000 primary school science diagrams. Lang. Resour. Eval.  5 (5), 661\u2013688 (2021).","journal-title":"Lang. Resour. Evaluation"},{"issue":"3","key":"78557_CR13","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1075\/target.18085.ram","volume":"32","author":"S Pinto","year":"2020","unstructured":"Pinto, S., Ramos & Mubaraki, A. Multimodal corpus analysis of subtitling: the case of non-standard varieties. Target. Int. J. Transl. Stud. 32 (3), 389\u2013419 (2020).","journal-title":"Int. J. Translation Stud."},{"issue":"2","key":"78557_CR14","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/s41701-024-00164-3","volume":"8","author":"J Anderson","year":"2024","unstructured":"Anderson, J., Asabea, E., Agbaglo & Rachel, G. A. Exploring ghanaians\u2019 usage of Ei, ehe, eh, and eish in global web-based English Corpus. Corpus Pragmat. 8 (2), 131\u2013148 (2024).","journal-title":"Corpus Pragmat."},{"issue":"7","key":"78557_CR15","first-page":"1043","volume":"18","author":"R Cave","year":"2023","unstructured":"Cave, R. & Bloch, S. The use of speech recognition technology by people living with amyotrophic lateral sclerosis: a sco** review. Disabil. Rehabil. Assist. Technol. 18 (7), 1043\u20131055 (2023).","journal-title":"Disabil. Rehabilitation: Assist. Technol."},{"key":"78557_CR16","doi-asserted-by":"crossref","unstructured":"Zhou, S. et al. A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises. Proceedings of the IEEE 109.5 : 820\u2013838. (2021).","DOI":"10.1109\/JPROC.2021.3054390"},{"issue":"9","key":"78557_CR17","doi-asserted-by":"crossref","first-page":"0912001","DOI":"10.3788\/AOS202141.0912001","volume":"41","author":"J Zhang","year":"2021","unstructured":"Zhang, J. Adaptive modulation method of structured light projection based on the bidirectional reflection distribution function model. Acta Optica Sin. 41 (9), 0912001 (2021).","journal-title":"Acta Optica Sinica"},{"key":"78557_CR18","doi-asserted-by":"crossref","unstructured":"Polat, H. and Saadin Oyucu. Building a speech and text corpus of Turkish: large corpus collection with initial speech recognition results. Symmetry  12.2 290. (2020).","DOI":"10.3390\/sym12020290"},{"issue":"5","key":"78557_CR19","doi-asserted-by":"publisher","first-page":"1450","DOI":"10.1111\/bjet.12993","volume":"51","author":"K Sharma","year":"2020","unstructured":"Sharma, K. & Giannakos, M. Multimodal data capabilities for learning: what can multimodal data tell us about learning? Br. J. Edu. Technol. 51 (5), 1450\u20131484 (2020).","journal-title":"Br. J. Edu. Technol."},{"issue":"5","key":"78557_CR20","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1162\/neco_a_01273","volume":"32","author":"J Gao","year":"2020","unstructured":"Gao, J., Li, P., Chen, Z. & Zhang, J. A survey on deep learning for multimodal data fusion. Neural Comput. 32 (5), 829\u2013864 (2020).","journal-title":"Neural Comput."},{"issue":"10","key":"78557_CR21","first-page":"1095","volume":"40","author":"J Lipkova","year":"2022","unstructured":"Lipkova, J. et al. Artificial intelligence for multimodal data integration in oncology. Cancer Cell  40 (10) 1095\u20131110. (2022).","journal-title":"Artif. Intell. Multimodal data Integr. Oncol. Cancer cell."},{"key":"78557_CR22","doi-asserted-by":"publisher","first-page":"2213","DOI":"10.1044\/2020_JSLHR-20-00268","volume":"64","author":"TJ Mahr","year":"2021","unstructured":"Mahr, T. J., Berisha, V., Kawabata, K., Liss, J. & Hustad, K. C. Performance of forced-alignment algorithms on children\u2019s speech. J. Speech Lang. Hear. Res. 64, 2213\u20132222 (2021).","journal-title":"J. Speech Lang. Hear. Res."},{"issue":"8","key":"78557_CR23","doi-asserted-by":"publisher","first-page":"4581","DOI":"10.1109\/TGRS.2018.2828029","volume":"56","author":"J Jiang","year":"2018","unstructured":"Jiang, J. SuperPCA: a superpixelwise PCA approach for unsupervised feature extraction of hyperspectral imagery. IEEE Trans. Geosci. Remote Sens. 56 (8), 4581\u20134593 (2018).","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"6","key":"78557_CR24","doi-asserted-by":"publisher","first-page":"3527","DOI":"10.1109\/TCSVT.2021.3116679","volume":"32","author":"B Chen","year":"2021","unstructured":"Chen, B., Liu, X., Zheng, Y., Zhao, G. & Shi, Y. Q. A robust GAN-generated face detection method based on dual-color spaces and an improved Xception. IEEE Trans. Circuits Syst. Video Technol. 32 (6), 3527\u20133538 (2021).","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"1","key":"78557_CR25","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1186\/s12903-023-03537-3","volume":"23","author":"AK Alshammari","year":"2023","unstructured":"Alshammari, A. K. et al. Influence of lip position on esthetics perception with respect to profile divergence using silhouette images. BMC Oral Health  23 (1), 791 (2023).","journal-title":"BMC Oral Health"},{"issue":"8","key":"78557_CR26","doi-asserted-by":"publisher","first-page":"10173","DOI":"10.1109\/TPAMI.2023.3250241","volume":"45","author":"L Huang","year":"2023","unstructured":"Huang, L. et al. Normalization techniques in training dnns: methodology, analysis and application. IEEE Trans. Pattern Anal. Mach. Intell. 45 (8), 10173\u201310196 (2023).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-78557-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-78557-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-78557-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T16:07:41Z","timestamp":1730909261000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-78557-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,6]]},"references-count":26,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["78557"],"URL":"https:\/\/doi.org\/10.1038\/s41598-024-78557-2","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,6]]},"assertion":[{"value":"21 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 November 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"27000"}}