{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T23:21:07Z","timestamp":1777072867378,"version":"3.51.4"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,6,11]],"date-time":"2020-06-11T00:00:00Z","timestamp":1591833600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,6,11]],"date-time":"2020-06-11T00:00:00Z","timestamp":1591833600000},"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":["SIViP"],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1007\/s11760-020-01717-0","type":"journal-article","created":{"date-parts":[[2020,6,11]],"date-time":"2020-06-11T08:02:42Z","timestamp":1591862562000},"page":"25-32","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Appearance and shape-based hybrid visual feature extraction: toward audio\u2013visual automatic speech recognition"],"prefix":"10.1007","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4246-3970","authenticated-orcid":false,"given":"Saswati","family":"Debnath","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pinki","family":"Roy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,6,11]]},"reference":[{"issue":"2","key":"1717_CR1","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/s10772-014-9257-1","volume":"18","author":"P Borde","year":"2015","unstructured":"Borde, P., Varpe, A., Manza, R., Yannawar, P.: Recognition of isolated words using Zernike and MFCC features for audio visual speech recognition. Int. J. Speech Technol. 18(2), 167\u2013175 (2015)","journal-title":"Int. J. Speech Technol."},{"issue":"4","key":"1717_CR2","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1007\/s10489-014-0629-7","volume":"42","author":"K Noda","year":"2015","unstructured":"Noda, K., Yamaguchi, Y., Nakadai, K., Okuno, H.G., Ogata, T.: Audio-visual speech recognition using deep learning. Appl. Intell. 42(4), 722\u2013737 (2015)","journal-title":"Appl. Intell."},{"issue":"9","key":"1717_CR3","doi-asserted-by":"publisher","first-page":"1306","DOI":"10.1109\/JPROC.2003.817150","volume":"91","author":"G Potamianos","year":"2003","unstructured":"Potamianos, G., Neti, C., Gravier, G., Garg, A., Senior, A.W.: Recent advances in the automatic recognition of audiovisual speech. Proc. IEEE 91(9), 1306\u20131326 (2003)","journal-title":"Proc. IEEE"},{"key":"1717_CR4","doi-asserted-by":"publisher","DOI":"10.14810\/ecij.2015.4403","author":"N Dave","year":"2015","unstructured":"Dave, N.: A lip localization based visual feature extraction method. Electr. Comput. Eng. Int. J. ECIJ (2015). https:\/\/doi.org\/10.14810\/ecij.2015.4403","journal-title":"Electr. Comput. Eng. Int. J. ECIJ"},{"issue":"1","key":"1717_CR5","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1007\/BF02884428","volume":"1","author":"AG Chitu","year":"2007","unstructured":"Chitu, A.G., Rothkrantz, L.J.M., Wojdel, J.C., Wiggers, P.: Comparison between different feature extraction techniques for audio-visual speech recognition. J. Multimodal User Interfaces 1(1), 7\u201320 (2007)","journal-title":"J. Multimodal User Interfaces"},{"issue":"3","key":"1717_CR6","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/6046.865479","volume":"2","author":"S Dupont","year":"2000","unstructured":"Dupont, S., Luettin, J.: Audio-Visual Speech Modeling for Continuous Speech Recognition. IEEE Trans. Multimedia 2(3), 141\u2013151 (2000)","journal-title":"IEEE Trans. Multimedia"},{"issue":"7","key":"1717_CR7","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1109\/TPAMI.2002.1017623","volume":"24","author":"T Ojala","year":"2002","unstructured":"Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. Trans. IEEE Pattern Anal. Mach. Intell 24(7), 971\u2013987 (2002)","journal-title":"Trans. IEEE Pattern Anal. Mach. Intell"},{"issue":"7","key":"1717_CR8","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/TMM.2009.2030637","volume":"11","author":"G Zhao","year":"2009","unstructured":"Zhao, G., Barnard, M., Pietikainen, M.: Lipreading with local spatiotemporal descriptors. Trans. IEEE Multimed. 11(7), 1254\u20131265 (2009)","journal-title":"Trans. IEEE Multimed."},{"issue":"4","key":"1717_CR9","doi-asserted-by":"publisher","first-page":"1431","DOI":"10.1016\/j.patcog.2009.11.001","volume":"43","author":"S Dabbaghchiana","year":"2010","unstructured":"Dabbaghchiana, S., Ghaemmaghamib, M.P., Aghagolzadeh, A.: Feature extraction using discrete cosine transform and discrimination power analysis with a face recognition technology. Pattern Recognit. 43(4), 1431\u20131440 (2010)","journal-title":"Pattern Recognit."},{"issue":"1","key":"1717_CR10","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1017\/S0305004100029066","volume":"50","author":"A Bhatia","year":"2002","unstructured":"Bhatia, A., Wolf, E.: On the circle polynomials of zernike and related orthogonal sets. Proc. Camb. Philos. Soc. 50(1), 40\u201348 (2002)","journal-title":"Proc. Camb. Philos. Soc."},{"issue":"1","key":"1717_CR11","first-page":"95","volume":"27","author":"C Singh","year":"2013","unstructured":"Singh, C., Upneja, R.: Accurate calculation of high order pseudo Zernike moments and their numerical stability. Digit. Signal Proc. 27(1), 95\u2013106 (2013)","journal-title":"Digit. Signal Proc."},{"key":"1717_CR12","doi-asserted-by":"crossref","unstructured":"Sato, H., Iwai, T.: A complex singular value decomposition algorithm based on the Riemannian Newton method. In: 52nd IEEE Conference on Decision and Control, Florence, Italy. IEEE (2013)","DOI":"10.1109\/CDC.2013.6760335"},{"issue":"2","key":"1717_CR13","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1109\/TCSVT.2018.2799214","volume":"29","author":"J Wen","year":"2019","unstructured":"Wen, J., Fang, X., Cui, J., Fei, L., Yan, K., Chen, Y., Xu, Y.: Robust sparse linear discriminant analysis. IEEE Trans. Circuits Syst. Video Technol. 29(2), 390\u2013403 (2019)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"4","key":"1717_CR14","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"SB Davis","year":"1980","unstructured":"Davis, S.B., Mermelstein, P.: Comparison of parametric representation for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust. Speech Signal Process. 28(4), 357\u2013365 (1980)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"1","key":"1717_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2298\/JAC1001001G","volume":"20","author":"VMW Gevaert","year":"2010","unstructured":"Gevaert, V.M.W., Tsenov, G.: Neural networks used for speech recognition. J. Autom. Control 20(1), 1\u20137 (2010)","journal-title":"J. Autom. Control"},{"issue":"8","key":"1717_CR16","doi-asserted-by":"publisher","first-page":"2348","DOI":"10.1109\/TSP.2004.831018","volume":"52","author":"A Ganapathiraju","year":"2004","unstructured":"Ganapathiraju, A., Jonathan, E., Picone, H.J.: Applications of support vector machines to speech recognition. IEEE Trans. Signal Process. 52(8), 2348\u20132355 (2004)","journal-title":"IEEE Trans. Signal Process."},{"key":"1717_CR17","volume-title":"Artificial Intelligence: A Modern Approach","author":"S Russell","year":"2003","unstructured":"Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach. Prentice Hall, Upper Saddle River (2003)"},{"key":"1717_CR18","doi-asserted-by":"publisher","DOI":"10.1002\/0471660264","volume-title":"Combining Pattern Classifiers: Methods and Algorithms","author":"LI Kuncheva","year":"2004","unstructured":"Kuncheva, L.I.: Combining Pattern Classifiers: Methods and Algorithms. Wiley, New York (2004)"},{"issue":"4","key":"1717_CR19","first-page":"25","volume":"137","author":"P Borde","year":"2004","unstructured":"Borde, P., Manza, R., Gawali, B., Yannawar, P.: \u2018VISWa\u2019: a multilingual multi-pose audio visual database for robust human computer interaction. Int. J. Comput. Appl. 137(4), 25\u201331 (2004)","journal-title":"Int. J. Comput. Appl."},{"issue":"8","key":"1717_CR20","doi-asserted-by":"publisher","first-page":"2554","DOI":"10.1016\/j.patcog.2015.02.005","volume":"48","author":"GH Liu","year":"2015","unstructured":"Liu, G.H., Yang, J.Y., Li, Z.: Content-based image retrieval using computational visual attention model. Pattern Recognit. 48(8), 2554\u20132566 (2015)","journal-title":"Pattern Recognit."},{"issue":"1","key":"1717_CR21","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1109\/TIP.2018.2847422","volume":"28","author":"GH Liu","year":"2019","unstructured":"Liu, G.H., Yang, J.Y.: Exploiting color volume and color difference for salient region detection. IEEE Trans. Image Process. 28(1), 6\u201316 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"1717_CR22","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.specom.2017.01.005","volume":"90","author":"C Sui","year":"2017","unstructured":"Sui, C., Togneri, R., Bennamoun, M.: A cascade gray-stereo visual feature extraction method for visual and audio-visual speech recognition. Speech Commun. 90, 26\u201338 (2017)","journal-title":"Speech Commun."}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-020-01717-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-020-01717-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-020-01717-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,11]],"date-time":"2021-06-11T00:01:46Z","timestamp":1623369706000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-020-01717-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,11]]},"references-count":22,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,2]]}},"alternative-id":["1717"],"URL":"https:\/\/doi.org\/10.1007\/s11760-020-01717-0","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6,11]]},"assertion":[{"value":"30 August 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 December 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 May 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 June 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}