{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T11:41:47Z","timestamp":1742643707944},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,11,2]],"date-time":"2021-11-02T00:00:00Z","timestamp":1635811200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,11,2]],"date-time":"2021-11-02T00:00:00Z","timestamp":1635811200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1007\/s00034-021-01880-w","type":"journal-article","created":{"date-parts":[[2021,11,2]],"date-time":"2021-11-02T17:51:20Z","timestamp":1635875480000},"page":"2152-2172","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Development of Visual-Only Speech Recognition System for Mute People"],"prefix":"10.1007","volume":"41","author":[{"given":"G. Aswanth","family":"Kumar","sequence":"first","affiliation":[]},{"given":"Jino Hans","family":"William","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,11,2]]},"reference":[{"key":"1880_CR1","unstructured":"F. Albu, D. Hagiescu, L. Vladutu, M.A. Puica, Neural network approaches for children\u2019s emotion recognition in intelligent learning applications, in EDULEARN15 7th Annual International Conference Education of New Learning Technology Barcelona, Spain, 6th-8th, pp. 3229\u20133239 (2015)"},{"key":"1880_CR2","doi-asserted-by":"crossref","unstructured":"I. Almajai, S. Cox, R. Harvey, Y. Lan, Improved speaker independent lip reading using speaker adaptive training and deep neural networks, in IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 2722\u20132726 (2016)","DOI":"10.1109\/ICASSP.2016.7472172"},{"key":"1880_CR3","doi-asserted-by":"crossref","unstructured":"E. Benhaim, H. Sahbi, G. Vittey, Continuous visual speech recognition for audio speech enhancement, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2244\u20132248 (2015)","DOI":"10.1109\/ICASSP.2015.7178370"},{"key":"1880_CR4","first-page":"669","volume":"2","author":"C Bregler","year":"1994","unstructured":"C. Bregler, Y. Kong, Eigenlips for robust speech recognition. IEEE Int. Conf. Acoust. Speech Signal Process. 2, 669\u2013672 (1994)","journal-title":"IEEE Int. Conf. Acoust. Speech Signal Process."},{"issue":"5","key":"1880_CR5","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/0964-1955(96)00002-4","volume":"32","author":"M Cattaruzza","year":"1996","unstructured":"M. Cattaruzza, P. Maisonneuve, P. Boyle, Epidemiology of laryngeal cancer. Eur. J. Cancer B Oral Oncol. 32(5), 293\u2013305 (1996)","journal-title":"Eur. J. Cancer B Oral Oncol."},{"key":"1880_CR6","unstructured":"S. Hilder, R.W. Harvey, B.J. Theobald, Comparison of human and machine-based lip- reading. AVSP pp. 86\u201389 (2009)"},{"key":"1880_CR7","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.inffus.2018.09.008","volume":"49","author":"MS Hossain","year":"2019","unstructured":"M.S. Hossain, G. Muhammad, Emotion recognition using deep learning approach from audiovisual emotional big data. Inform. Fusion 49, 69\u201378 (2019)","journal-title":"Inform. Fusion"},{"key":"1880_CR8","unstructured":"A.G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, H. Adam, Mobilenets: efficient convolutional neural networks for mobile vision applications (2017)"},{"key":"1880_CR9","unstructured":"O.H. Jensen, Implementing the Viola-Jones face detection algorithm (Master\u2019s thesis). DTU, DK-2800 Kgs. Lyngby, Denmark (2008)"},{"key":"1880_CR10","unstructured":"T. Kanade, J. Cohn, Y. Tian, Comprehensive database for facial expression analysis, in Proceedings of the International Conference on Automatic Face and Gesture Recognition, pp. 46\u201353 (2000)"},{"key":"1880_CR11","doi-asserted-by":"crossref","unstructured":"Y. Lan, R. Harvey, B. Theobald, Insights into machine lip reading, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4825\u20134828 (2012)","DOI":"10.1109\/ICASSP.2012.6288999"},{"key":"1880_CR12","doi-asserted-by":"publisher","first-page":"794","DOI":"10.1109\/ACCESS.2017.2649838","volume":"5","author":"B Lin","year":"2017","unstructured":"B. Lin, Y. Yao, C. Liu, C. Lien, Development of novel lip-reading recognition algorithm. IEEE Access 5, 794\u2013801 (2017)","journal-title":"IEEE Access"},{"key":"1880_CR13","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1016\/j.inffus.2018.06.003","volume":"46","author":"Y Ma","year":"2019","unstructured":"Y. Ma, Y. Hao, M. Chen, J. Chen, P. Lu, A. Ko\u0161ir, Audio-visual emotion fusion (AVEF): a deep efficient weighted approach. Inform. Fusion 46, 184\u2013192 (2019)","journal-title":"Inform. Fusion"},{"key":"1880_CR14","doi-asserted-by":"crossref","unstructured":"A. Neubeck, L.V. Gool, Efficient non-maximum suppression, in Proceedings of the 18th International Conference on Pattern Recognition (ICPR\u201906) 3, pp. 850\u2013855 (2006)","DOI":"10.1109\/ICPR.2006.479"},{"issue":"5","key":"1880_CR15","doi-asserted-by":"publisher","first-page":"1018","DOI":"10.1109\/TMI.2014.2366792","volume":"34","author":"AV Opbroek","year":"2015","unstructured":"A.V. Opbroek, M.A. Ikram, M.W. Vernooij, M. de Bruijne, Transfer learning improves supervised image segmentation across imaging protocols. IEEE Trans. Med. Imag. 34(5), 1018\u20131030 (2015)","journal-title":"IEEE Trans. Med. Imag."},{"issue":"3","key":"1880_CR16","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1044\/jshr.2803.381","volume":"28","author":"E Owens","year":"1985","unstructured":"E. Owens, B. Blazek, Visemes observed by hearing-impaired and normal-hearing adult viewers. J. Speech Lang. Hear. Res. 28(3), 381\u2013393 (1985)","journal-title":"J. Speech Lang. Hear. Res."},{"key":"1880_CR17","doi-asserted-by":"crossref","unstructured":"S. Petridis, A. Asghar, M. Pantic, Classifying laughter and speech using audio-visual feature prediction, in IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 5254\u20135257 (2010)","DOI":"10.1109\/ICASSP.2010.5494992"},{"key":"1880_CR18","doi-asserted-by":"crossref","unstructured":"S. Petridis, M. Pantic, Deep complementary bottleneck features for visual speech recognition, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shangai, pp. 2304\u20132308 (2016)","DOI":"10.1109\/ICASSP.2016.7472088"},{"key":"1880_CR19","doi-asserted-by":"crossref","unstructured":"S. Petridis, J. Shen, D. Cetin, M. Pantic, Visual-only recognition of normal, whispered and silent speech, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6219\u20136233 (2018)","DOI":"10.1109\/ICASSP.2018.8461596"},{"key":"1880_CR20","doi-asserted-by":"crossref","unstructured":"A. Rekik, A. Ben-Hamadou, W. Mahdi, A new visual speech recognition approach for RGB-D cameras, in Proceedings of the 11th International Conference on Image Analysis and Recognition (ICIAR), pp. 21\u201328 (2014)","DOI":"10.1007\/978-3-319-11755-3_3"},{"key":"1880_CR21","unstructured":"K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition (2014)"},{"key":"1880_CR22","doi-asserted-by":"crossref","unstructured":"T. Stafylakis, S. Petridis, P. Ma, F. Cai, G. Tzimiropoulos, M. Pantic, End-to-End audiovisual speech recognition, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6548\u20136552 (2018)","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"1880_CR23","doi-asserted-by":"crossref","unstructured":"M. Wand, J. Koutn\u00edk, J. Schmidhuber, Lipreading with long short-term memory, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6115\u20136119 (2016)","DOI":"10.1109\/ICASSP.2016.7472852"},{"key":"1880_CR24","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1016\/j.inffus.2017.10.006","volume":"42","author":"Q Zhang","year":"2018","unstructured":"Q. Zhang, L.T. Yang, Z. Chen, P. Li, A survey on deep learning for big data. Inform. Fusion 42, 146\u2013157 (2018)","journal-title":"Inform. Fusion"}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-021-01880-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00034-021-01880-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-021-01880-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T11:08:31Z","timestamp":1646132911000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00034-021-01880-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,2]]},"references-count":24,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["1880"],"URL":"https:\/\/doi.org\/10.1007\/s00034-021-01880-w","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"value":"0278-081X","type":"print"},{"value":"1531-5878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,2]]},"assertion":[{"value":"2 September 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 October 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 October 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 November 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declaration"}},{"value":"The authors declare that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}