{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T10:45:18Z","timestamp":1761561918498},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2014,10,21]],"date-time":"2014-10-21T00:00:00Z","timestamp":1413849600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2015,6]]},"DOI":"10.1007\/s10772-014-9257-1","type":"journal-article","created":{"date-parts":[[2014,10,22]],"date-time":"2014-10-22T00:37:11Z","timestamp":1413938231000},"page":"167-175","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":38,"title":["Recognition of isolated words using Zernike and MFCC features for audio visual speech recognition"],"prefix":"10.1007","volume":"18","author":[{"given":"Prashant","family":"Borde","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amarsinh","family":"Varpe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ramesh","family":"Manza","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pravin","family":"Yannawar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,10,21]]},"reference":[{"key":"9257_CR1","volume-title":"Pattern recognition and machine learning","author":"CM Bishop","year":"2006","unstructured":"Bishop, C. M. (2006). Pattern recognition and machine learning. heidelberg: Springer."},{"key":"9257_CR2","volume-title":"Learning Open CV: Computer vision with the OpenCV library","author":"G Bradski","year":"2008","unstructured":"Bradski, G., & Kaehler, A. (2008). Learning Open CV: Computer vision with the OpenCV library (1st ed.). CA, USA: O\u2019Reilly Media.","edition":"1"},{"key":"9257_CR3","doi-asserted-by":"crossref","unstructured":"Capiler, A. (2001). Lip detection and tracking, 11th International Conference on Image Analysis and Processing (ICIAP 2001), Palermo, Italy","DOI":"10.1109\/ICIAP.2001.956978"},{"key":"9257_CR4","unstructured":"Christopher, B. (1993). Improving connected letter recognition by Lip-reading, IEEE (pp. 361\u2013365)."},{"key":"9257_CR5","volume-title":"Discrete-Time Processing of Speech Signals","author":"JR Deller","year":"1993","unstructured":"Deller, J. R., Proakis, J. G., & Hansen, J. H. L. (1993). Discrete-Time Processing of Speech Signals. Englewood Cliffs: Macmillan Publishing Company."},{"key":"9257_CR6","doi-asserted-by":"crossref","unstructured":"Duchnowski, P. (1995). Toward movement invariant automatic lip-reading and speech recognition, IEEE, pp.109\u2013111","DOI":"10.1109\/ICASSP.1995.479285"},{"key":"9257_CR7","unstructured":"Finn K.I. (1986). An investigation of visible lip information to be used in automated speech recognition. Ph.D Thesis, George-Town University."},{"key":"9257_CR8","volume-title":"Speech and audio signal processing","author":"B Gold","year":"2000","unstructured":"Gold, B., & Morgan, N. (2000). Speech and audio signal processing. New York, NY: John Wiley and Sons."},{"key":"9257_CR9","doi-asserted-by":"crossref","unstructured":"Hong, X, et al. (2006). A PCA based visual DCT feature extraction method for lip-reading. International Conference on Intelligent Information Hiding and Multimedia Signal Processing.","DOI":"10.1109\/IIH-MSP.2006.265008"},{"key":"9257_CR10","doi-asserted-by":"crossref","unstructured":"Hwang, S-K., Kim, W-Y. \u201cA novel approach to the fast computation of Zernike moments\u201d,The Journal of the Pattern Recognition Society, doi: 10.1016\/j.patcog.2006.03.004 .","DOI":"10.1016\/j.patcog.2006.03.004"},{"key":"9257_CR11","unstructured":"Juergen, L. (1996). Visual speech recognition using active shape model and hidden markov model, IEEE, pp.817\u2013820"},{"key":"9257_CR12","unstructured":"Leon, C. G. K., Perai, P. S., Pauh, J. P. (2009). \u201cRobust Computer Voice Recognition Using Improved MFCC Algorithm\u201d, International Conference on New Trends in Information and Service Science."},{"key":"9257_CR13","doi-asserted-by":"crossref","unstructured":"Li, M., Cheung, M. (2008). A Novel motion based lip feature extraction for lip-reading, IEEE International Conference on Computational Intelligence and Security (pp. 361\u2013365). Sichan Province, China","DOI":"10.1109\/CIS.2008.214"},{"key":"9257_CR14","doi-asserted-by":"crossref","first-page":"253","DOI":"10.3758\/BF03206096","volume":"24","author":"J Macdonald","year":"1978","unstructured":"Macdonald, J., & MacGurk, H. (1978). Visual influences on speech perception process. Perception and Psychophysics, 24, 253\u2013257.","journal-title":"Perception and Psychophysics"},{"key":"9257_CR15","doi-asserted-by":"crossref","first-page":"746","DOI":"10.1038\/264746a0","volume":"264","author":"H MacGurk","year":"1976","unstructured":"MacGurk, H., & Macdonald, J. (1976). Hearing lips and seeing voices. Nature, 264, 746\u2013748.","journal-title":"Nature"},{"key":"9257_CR16","first-page":"87","volume":"268","author":"FJ Malkin","year":"1986","unstructured":"Malkin, F. J. (1986). The effect on computer recognition of speech when speaking through protective masks. Proceeding Speech Technology, 268, 87\u2013265.","journal-title":"Proceeding Speech Technology"},{"key":"9257_CR17","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1109\/34.982900","volume":"24","author":"L Matthews","year":"2002","unstructured":"Matthews, L., Cootes, T. F., Banbham, J. A., Cox, S., & Harvey, R. (2002). Extraction of visual features of lip-reading. IEEE Transaction on Pattern Analysis and Machine Intelligence, 24, 198\u2013213.","journal-title":"IEEE Transaction on Pattern Analysis and Machine Intelligence"},{"key":"9257_CR18","first-page":"10","volume":"87","author":"WS Meisel","year":"1987","unstructured":"Meisel, W. S. (1987). A natural speech recognition system. Proceeding Speech Technology, 87, 10\u201313.","journal-title":"Proceeding Speech Technology"},{"key":"9257_CR19","unstructured":"Moody, T., Joost, M., & Rodman, R. (1987). A comparative evaluation a speech recognizers. Proceeding Speech Technology, 87, 275\u2013280."},{"key":"9257_CR20","unstructured":"Neti, C., et al. (Oct 2000) audio-visual speech recognition, Workshop 2000 Final report."},{"key":"9257_CR21","unstructured":"Paul, D. B., Lippmann, R. P., Chen, Y., & Weinstein, C. J. (1987). Robust HMM based technique for recognition of speech Produced under stress and in noise. Proceeding Speech Technology, 87, 275\u2013280."},{"key":"9257_CR22","unstructured":"Petjan, E., Bischoff, B., & Bodoff, D. (1987). An Improved automatic Lip-reading system to enhance speech Recognition, Technical Report TM 11251\u2013871012-11, AT&T Bell Labs"},{"key":"9257_CR23","unstructured":"Saitoh, T., Morishita, K. & Konishi, R. (2008). Analysis of efficient lip-reading method for various languages, In Pattern Recognition, ICPR 2008. 19th International Conference on IEEE (pp. 1\u20134). Florida, USA"},{"key":"9257_CR24","doi-asserted-by":"crossref","unstructured":"Sum, K.L., et al. (2001). A new optimization procedure for extracting the point based lip contour using active shape model. In Acoustics, Speech, and Signal Processing. Proceedings of (ICASSP\u201901) 2001 IEEE International Conference ( pp. 1485\u20131488).","DOI":"10.1109\/ICASSP.2001.941212"},{"key":"9257_CR25","unstructured":"Tiwari, V. (2010). MFCC and its applications in speaker recognition. Dept. of Electronics Engg., Gyan Ganga Institute of Technology and Management, Bhopal, (MP). arxiv.org."},{"issue":"8","key":"9257_CR26","doi-asserted-by":"crossref","first-page":"0975","DOI":"10.5120\/1227-1785","volume":"8","author":"J Tripathy","year":"2010","unstructured":"Tripathy, J. (2010). Reconstruction of oriya alphabets using Zernike moments. International Journal of Computer Applications, 8(8), 0975\u20138887.","journal-title":"International Journal of Computer Applications"},{"key":"9257_CR27","doi-asserted-by":"crossref","unstructured":"Yuhas, B.P., Goldstien, M.H. & Sejnowski, T.J. (1989). Integration of acoustic and visual speech signals using neural networks, IEEE Communication Magazine, pp. 65\u201371","DOI":"10.1109\/35.41402"},{"key":"9257_CR28","unstructured":"\u017delezn\u00fd, M., Kr\u0148oul, Z., C\u00edsa\u0159, P., Matou\u0161ek, J. (2006). Design, implementation and evaluation of the Czech realistic audio-visual speech synthesis. Signal Processing, vol. 86, no. 12, New York: Elsevier Science (ISSN 0165\u20131684)."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-014-9257-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-014-9257-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-014-9257-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,30]],"date-time":"2019-05-30T20:02:47Z","timestamp":1559246567000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-014-9257-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,10,21]]},"references-count":28,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2015,6]]}},"alternative-id":["9257"],"URL":"https:\/\/doi.org\/10.1007\/s10772-014-9257-1","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,10,21]]}}}