{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T21:04:06Z","timestamp":1774991046556,"version":"3.50.1"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T00:00:00Z","timestamp":1749081600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T00:00:00Z","timestamp":1749081600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s11760-025-04178-5","type":"journal-article","created":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T19:16:17Z","timestamp":1749150977000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Lips movement detection and conversion into text using deep learning-based CNN model"],"prefix":"10.1007","volume":"19","author":[{"given":"Abdullah Bin Younas","family":"Awan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naqash","family":"Younas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad","family":"Fahad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanzhang","family":"Geng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,5]]},"reference":[{"key":"4178_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2023.107718","volume":"143","author":"H Shen","year":"2023","unstructured":"Shen, H., Wang, M.: Effects of social skills on lexical alignment in human-human interaction and human-computer interaction. Comput. Human Behav. 143, 107718 (2023)","journal-title":"Comput. Human Behav."},{"key":"4178_CR2","doi-asserted-by":"crossref","unstructured":"Zhao, X., Jia, X., Zhang, T., Cao, Y., Liu, T.: Evolutionary algorithms with blind fitness evaluation for solving optimization problems with only fuzzy fitness information. IEEE Transactions on Fuzzy Systems (2023)","DOI":"10.1109\/TFUZZ.2023.3273308"},{"key":"4178_CR3","doi-asserted-by":"crossref","unstructured":"Beaudouin-Lafon, M.: Human-computer interaction. In: Interactive Computation: The New Paradigm, pp. 227\u2013254. Springer, ??? (2006)","DOI":"10.1007\/3-540-34874-3_10"},{"key":"4178_CR4","doi-asserted-by":"publisher","first-page":"9411","DOI":"10.1007\/s11042-020-10073-7","volume":"80","author":"M Malik","year":"2021","unstructured":"Malik, M., Malik, M.K., Mehmood, K., Makhdoom, I.: Automatic speech recognition: a survey. Multimedia Tools Appl 80, 9411\u20139457 (2021)","journal-title":"Multimedia Tools Appl"},{"key":"4178_CR5","doi-asserted-by":"crossref","unstructured":"Solera-Ure\u00f1a, R., Padrell-Sendra, J., Mart\u00edn-Iglesias, D., Gallardo-Antol\u00edn, A., Pel\u00e1ez-Moreno, C., D\u00edaz-de-Mar\u00eda, F.: Svms for automatic speech recognition: a survey. Progress in nonlinear speech processing, 190\u2013216 (2007)","DOI":"10.1007\/978-3-540-71505-4_11"},{"key":"4178_CR6","doi-asserted-by":"crossref","unstructured":"Rabiner, L., Juang, B.-H., Lee, C.-H.: An overview of automatic speech recognition. Automatic speech and speaker recognition: advanced topics, 1\u201330 (1996)","DOI":"10.1007\/978-1-4613-1367-0_1"},{"issue":"2","key":"4178_CR7","doi-asserted-by":"publisher","first-page":"1617","DOI":"10.1007\/s00500-020-05248-1","volume":"25","author":"Y Kumar","year":"2021","unstructured":"Kumar, Y., Singh, N., Kumar, M., Singh, A.: Autossr: an efficient approach for automatic spontaneous speech recognition model for the punjabi language. Soft Comput. 25(2), 1617\u20131630 (2021)","journal-title":"Soft Comput."},{"key":"4178_CR8","doi-asserted-by":"crossref","unstructured":"O\u2019Shaughnessy, D.: Understanding automatic speech recognition. Computer Speech & Language, 101538 (2023)","DOI":"10.1016\/j.csl.2023.101538"},{"issue":"1824","key":"4178_CR9","doi-asserted-by":"publisher","first-page":"20200192","DOI":"10.1098\/rstb.2020.0192","volume":"376","author":"D Dediu","year":"2021","unstructured":"Dediu, D., Moisik, S.R., Baetsen, W., Bosman, A.M., Waters-Rist, A.L.: The vocal tract as a time machine: inferences about past speech and language from the anatomy of the speech organs. Philos. Trans. Royal Soc. B 376(1824), 20200192 (2021)","journal-title":"Philos. Trans. Royal Soc. B"},{"issue":"1","key":"4178_CR10","doi-asserted-by":"publisher","first-page":"928","DOI":"10.1038\/s41598-022-26155-5","volume":"13","author":"H Laux","year":"2023","unstructured":"Laux, H., Hallawa, A., Assis, J.C.S., Schmeink, A., Martin, L., Peine, A.: Two-stage visual speech recognition for intensive care patients. Sci. Rep. 13(1), 928 (2023)","journal-title":"Sci. Rep."},{"issue":"4","key":"4178_CR11","doi-asserted-by":"publisher","first-page":"1834","DOI":"10.3390\/s23041834","volume":"23","author":"Y He","year":"2023","unstructured":"He, Y., Seng, K.P., Ang, L.M.: Multimodal sensor-input architecture with deep learning for audio-visual speech recognition in wild. Sensors 23(4), 1834 (2023)","journal-title":"Sensors"},{"key":"4178_CR12","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1007\/s10590-020-09250-0","volume":"34","author":"U Sulubacak","year":"2020","unstructured":"Sulubacak, U., Caglayan, O., Gr\u00f6nroos, S.-A., Rouhe, A., Elliott, D., Specia, L., Tiedemann, J.: Multimodal machine translation through visuals and speech. Mach. Transl. 34, 97\u2013147 (2020)","journal-title":"Mach. Transl."},{"key":"4178_CR13","doi-asserted-by":"crossref","unstructured":"Gu, Y., Wang, X., Xie, L., Dong, C., Li, G., Shan, Y., Cheng, M.-M.: Vqfr: Blind face restoration with vector-quantized dictionary and parallel decoder. In: European Conference on Computer Vision, pp. 126\u2013143 (2022). Springer","DOI":"10.1007\/978-3-031-19797-0_8"},{"issue":"3","key":"4178_CR14","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1007\/s10846-021-01332-2","volume":"101","author":"C Strathearn","year":"2021","unstructured":"Strathearn, C., Ma, E.M.: A novel speech to mouth articulation system for realistic humanoid robots. J. Intell. Robot. Syst. 101(3), 54 (2021)","journal-title":"J. Intell. Robot. Syst."},{"key":"4178_CR15","doi-asserted-by":"crossref","unstructured":"Cho, C.J., Wu, P., Mohamed, A., Anumanchipalli, G.K.: Evidence of vocal tract articulation in self-supervised learning of speech. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135 (2023). IEEE","DOI":"10.1109\/ICASSP49357.2023.10094711"},{"issue":"4","key":"4178_CR16","doi-asserted-by":"publisher","first-page":"5455","DOI":"10.1007\/s11042-022-12796-1","volume":"82","author":"S Bhaskar","year":"2023","unstructured":"Bhaskar, S., Thasleema, T.: Lstm model for visual speech recognition through facial expressions. Multimedia Tools Appl. 82(4), 5455\u20135472 (2023)","journal-title":"Multimedia Tools Appl."},{"issue":"1","key":"4178_CR17","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1007\/s11042-022-13321-0","volume":"82","author":"M Miled","year":"2023","unstructured":"Miled, M., Messaoud, M.A.B., Bouzid, A.: Lip reading of words with lip segmentation and deep learning. Multimedia Tools Appl. 82(1), 551\u2013571 (2023)","journal-title":"Multimedia Tools Appl."},{"issue":"1","key":"4178_CR18","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1186\/s13638-023-02283-y","volume":"2023","author":"G Xing","year":"2023","unstructured":"Xing, G., Han, L., Zheng, Y., Zhao, M.: Application of deep learning in mandarin chinese lip-reading recognition. EURASIP J. Wireless Commun. Netw. 2023(1), 90 (2023)","journal-title":"EURASIP J. Wireless Commun. Netw."},{"key":"4178_CR19","doi-asserted-by":"crossref","unstructured":"Rundo, L., Han, C., Zhang, J., Hataya, R., Nagano, Y., Militello, C., Ferretti, C., Nobile, M.S., Tangherloni, A., Gilardi, M.C., et al.: Cnn-based prostate zonal segmentation on t2-weighted mr images: a cross-dataset study. Neural Approaches to Dynamics of Signal Exchanges, 269\u2013280 (2020)","DOI":"10.1007\/978-981-13-8950-4_25"},{"key":"4178_CR20","doi-asserted-by":"crossref","unstructured":"Novoz\u00e1msk\u1ef3, A., V\u00edt, D., \u0160roubek, F., Franc, J., Krb\u00e1lek, M., B\u00edlkova, Z., Zitov\u00e1, B.: Automated object labeling for cnn-based image segmentation. In: 2020 IEEE International Conference on Image Processing (ICIP), pp. 2036\u20132040 (2020). IEEE","DOI":"10.1109\/ICIP40778.2020.9191320"},{"key":"4178_CR21","doi-asserted-by":"publisher","first-page":"2018","DOI":"10.1109\/LSP.2022.3205481","volume":"29","author":"R Wang","year":"2022","unstructured":"Wang, R., Yang, Z., You, W., Zhou, L., Chu, B.: Fake face images detection and identification of celebrities based on semantic segmentation. IEEE Signal Process. Lett. 29, 2018\u20132022 (2022)","journal-title":"IEEE Signal Process. Lett."},{"issue":"17","key":"4178_CR22","doi-asserted-by":"publisher","first-page":"3619","DOI":"10.3390\/electronics12173619","volume":"12","author":"J-S Kim","year":"2023","unstructured":"Kim, J.-S., Park, S.-W., Kim, J.-Y., Park, J., Huh, J.-H., Jung, S.-H., Sim, C.-B.: E-hrnet: Enhanced semantic segmentation using squeeze and excitation. Electronics 12(17), 3619 (2023)","journal-title":"Electronics"},{"key":"4178_CR23","doi-asserted-by":"crossref","unstructured":"Lee, J., Lee, J., Yoo, S.: Real-time deblurring network for face ar applications. In: Proceedings of the 19th International Conference on Content-based Multimedia Indexing, pp. 91\u201396 (2022)","DOI":"10.1145\/3549555.3549577"},{"key":"4178_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdent.2022.104238","volume":"124","author":"F Preda","year":"2022","unstructured":"Preda, F., Morgan, N., Van Gerven, A., Nogueira-Reis, F., Smolders, A., Wang, X., Nomidis, S., Shaheen, E., Willems, H., Jacobs, R.: Deep convolutional neural network-based automated segmentation of the maxillofacial complex from cone-beam computed tomography: A validation study. J. Dent. 124, 104238 (2022)","journal-title":"J. Dent."},{"key":"4178_CR25","doi-asserted-by":"publisher","first-page":"1611","DOI":"10.1007\/s11036-019-01366-9","volume":"25","author":"M Sajjad","year":"2020","unstructured":"Sajjad, M., Zahir, S., Ullah, A., Akhtar, Z., Muhammad, K.: Human behavior understanding in big multimedia data using cnn based facial expression recognition. Mobile Netw. Appl. 25, 1611\u20131621 (2020)","journal-title":"Mobile Netw. Appl."},{"key":"4178_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wang, Y., Tang, Z., Li, Y., Chen, Y., Ling, H., Lin, W.: Gsto: Gated scale-transfer operation for multi-scale feature learning in semantic segmentation. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 7111\u20137118 (2021). IEEE","DOI":"10.1109\/ICPR48806.2021.9412965"},{"issue":"7","key":"4178_CR27","first-page":"1242","volume":"28","author":"C Guan","year":"2019","unstructured":"Guan, C., Wang, S., Liew, A.W.-C.: Lip image segmentation based on a fuzzy convolutional neural network. IEEE Trans. Fuzzy Syst. 28(7), 1242\u20131251 (2019)","journal-title":"IEEE Trans. Fuzzy Syst."},{"issue":"01","key":"4178_CR28","doi-asserted-by":"publisher","first-page":"2550001","DOI":"10.1142\/S0219467825500019","volume":"25","author":"C Jannu","year":"2023","unstructured":"Jannu, C., Vanambathina, S.D.: An overview of speech enhancement based on deep learning techniques. Int. J. Image Graphics 25(01), 2550001 (2023)","journal-title":"Int. J. Image Graphics"},{"key":"4178_CR29","doi-asserted-by":"publisher","unstructured":"Jannu, C., Vanambathina, S.D.: An attention based densely connected u-net with convolutional gru for speech enhancement. In: 2023 3rd International Conference on Artificial Intelligence and Signal Processing (AISP), pp. 1\u20135 (2023). https:\/\/doi.org\/10.1109\/AISP57993.2023.10134933","DOI":"10.1109\/AISP57993.2023.10134933"},{"issue":"12","key":"4178_CR30","doi-asserted-by":"publisher","first-page":"7467","DOI":"10.1007\/s00034-023-02455-7","volume":"42","author":"C Jannu","year":"2023","unstructured":"Jannu, C., Vanambathina, S.D.: Multi-stage progressive learning-based speech enhancement using time-frequency attentive squeezed temporal convolutional networks. Circuits Syst. Signal Process. 42(12), 7467\u20137493 (2023)","journal-title":"Circuits Syst. Signal Process."},{"issue":"1","key":"4178_CR31","first-page":"1195","volume":"45","author":"C Jannu","year":"2023","unstructured":"Jannu, C., Vanambathina, S.D.: Dct based densely connected convolutional gru for real-time speech enhancement. J. Intell. Fuzzy Syst. 45(1), 1195\u20131208 (2023)","journal-title":"J. Intell. Fuzzy Syst."},{"key":"4178_CR32","doi-asserted-by":"crossref","unstructured":"Parisae, V., Bhavanam, S.N.: Multi scale encoder-decoder network with time frequency attention and s-tcn for single channel speech enhancement. Journal of Intelligent & Fuzzy Systems (Preprint), 1\u201316 (2024)","DOI":"10.3233\/JIFS-233312"},{"key":"4178_CR33","doi-asserted-by":"crossref","unstructured":"Yang, S., Zhang, Y., Feng, D., Yang, M., Wang, C., Xiao, J., Long, K., Shan, S., Chen, X.: Lrw-1000: A naturally-distributed large-scale benchmark for lip reading in the wild. In: 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019), pp. 1\u20138 (2019). IEEE","DOI":"10.1109\/FG.2019.8756582"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04178-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-04178-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04178-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T14:41:41Z","timestamp":1751553701000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-04178-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,5]]},"references-count":33,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["4178"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-04178-5","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,5]]},"assertion":[{"value":"13 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 November 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 June 2025","order":4,"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 Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}}],"article-number":"691"}}