{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,6,22]],"date-time":"2024-06-22T22:38:41Z","timestamp":1719095921704},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2016,1,23]],"date-time":"2016-01-23T00:00:00Z","timestamp":1453507200000},"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":[[2016,3]]},"DOI":"10.1007\/s10772-016-9332-x","type":"journal-article","created":{"date-parts":[[2016,1,23]],"date-time":"2016-01-23T15:57:25Z","timestamp":1453564645000},"page":"159-171","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["Multiple cameras audio visual speech recognition using active appearance model visual features in car environment"],"prefix":"10.1007","volume":"19","author":[{"given":"Astik","family":"Biswas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"P. K.","family":"Sahu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahesh","family":"Chandra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,1,23]]},"reference":[{"key":"9332_CR5","doi-asserted-by":"crossref","first-page":"614","DOI":"10.1016\/j.procs.2015.07.417","volume":"57","author":"A Biswas","year":"2015","unstructured":"Biswas, A., Sahu, P., Bhowmick, A., & Chandra, M. (2015). AAM based features for multiple camera visual speech recognition in car environment. Procedia Computer Science, 57, 614\u2013621.","journal-title":"Procedia Computer Science"},{"issue":"4","key":"9332_CR15","doi-asserted-by":"crossref","first-page":"1111","DOI":"10.1016\/j.compeleceng.2014.01.008","volume":"40","author":"A Biswas","year":"2014","unstructured":"Biswas, A., Sahu, P. K., & Chandra, M. (2014). Admissible wavelet packet features based on human inner ear frequency response for hindi consonant recognition. Computers & Electrical Engineering (Elsevier), 40(4), 1111\u20131122.","journal-title":"Computers & Electrical Engineering (Elsevier)"},{"key":"9332_CR16","unstructured":"Chien, J.-T., Lai, J.-R., Lai, P.-Y. (2001). Microphone array signal processing for far-talking speech recognition. In IEEE Third Workshop on Signal Processing Advances in Wireless Communications, (pp. 322\u2013325)."},{"key":"9332_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1007\/BFb0054760","volume-title":"Active appearance models","author":"TF Cootes","year":"1998","unstructured":"Cootes, T. F., Edwards, G. J., & Taylor, C. J. (1998). Active appearance models (pp. 484\u2013498). Lecture Notes in Computer Science Heidelberg: Springer."},{"key":"9332_CR14","doi-asserted-by":"crossref","unstructured":"Davis, S. B., & Mermelstein, P. (1980). Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. In IEEE Transactions on Acoustic Speech Signal Process ASSP-28 (357\u2013366).","DOI":"10.1109\/TASSP.1980.1163420"},{"issue":"1","key":"9332_CR7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1687-6180-2012-51","volume":"2012","author":"V Estellers","year":"2012","unstructured":"Estellers, V., & Thiran, J.-P. (2012). Multi-pose lipreading and audio-visual speech recognition. EURASIP Journal on Advances in Signal Processing, 2012(1), 1\u201323.","journal-title":"EURASIP Journal on Advances in Signal Processing"},{"key":"9332_CR18","doi-asserted-by":"crossref","unstructured":"Faubel, F., Georges, M., Kumatani, K., Bruhn, A., & Klakow, D. (2011). Improving hands-free speech recognition in a car through audio-visual voice activity detection. In Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA), (pp. 70\u201375).","DOI":"10.1109\/HSCMA.2011.5942412"},{"issue":"2","key":"9332_CR13","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1109\/TSMCC.2009.2035631","volume":"40","author":"X Gao","year":"2010","unstructured":"Gao, X., Su, Y., Li, X., & Tao, D. (2010). A review of active appearance models. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 40(2), 145\u2013158.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews"},{"key":"9332_CR22","unstructured":"Irwin, A. (2008). Investigating the effects of accent on visual speech, Ph.D. thesis, University of Nottingham."},{"issue":"1","key":"9332_CR1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.specom.2004.01.003","volume":"43","author":"MN Kaynak","year":"2004","unstructured":"Kaynak, M. N., Zhi, Q., Cheok, A. D., Sengupta, K., Jian, Z., & Chung, K. C. (2004). Lip geometric features for human-computer interaction using bimodal speech recognition: comparison and analysis. Speech Communication, 43(1), 1\u201316.","journal-title":"Speech Communication"},{"key":"9332_CR10","unstructured":"Kleinschmidt, T., Dean, D., Sridharan, S., Mason, M. (2007). A continuous speech recognition evaluation protocol for the AVICAR database. In In proceedings of the International Conference on Signal Processing and Communication Systems (pp. 339\u2013344)."},{"issue":"14","key":"9332_CR20","first-page":"1641","volume":"37","author":"KF Lee","year":"1989","unstructured":"Lee, K. F., & Hon, H. W. (1989). Speaker-independent phone recognition using hidden Markov models. IEEE Transactions of Acoustics, Speech and Signal Processing, 37(14), 1641\u20131648.","journal-title":"IEEE Transactions of Acoustics, Speech and Signal Processing"},{"key":"9332_CR9","doi-asserted-by":"crossref","unstructured":"Lee, B., Hasegawa-Johnson, M., Goudeseune, C., Kamdar, S., Borys, S., Liu, M., & Huang, T. S. (2004). AVICAR: Audio-visual speech corpus in a car environment. In INTERSPEECH (pp. 2489\u20132492). Jeju Island.","DOI":"10.21437\/Interspeech.2004-424"},{"key":"9332_CR4","doi-asserted-by":"crossref","unstructured":"Lucey, P., & Potamianos, G. (2006). Lipreading using profile versus frontal views. In IEEE 8th Workshop on Multimedia Signal Processing (pp. 24\u201328).","DOI":"10.1109\/MMSP.2006.285261"},{"issue":"4","key":"9332_CR8","doi-asserted-by":"crossref","first-page":"911","DOI":"10.1016\/j.csl.2012.07.005","volume":"27","author":"R Navarathna","year":"2013","unstructured":"Navarathna, R., Dean, D., Sridharan, S., & Lucey, P. (2013). Multiple cameras for audio-visual speech recognition in an automotive environment. Computer Speech & Language, 27(4), 911\u2013927.","journal-title":"Computer Speech & Language"},{"key":"9332_CR11","unstructured":"Navarathna, R., Dean, D. B., Lucey, P. J., Sridharan, S., & Fookes, C. B. (2010). Recognising audio-visual speech in vehicles using the AVICAR database. In Proceedings of the 13th Australasian International Conference on Speech Science and Technology, The Australasian Speech Science & Technology Association (pp. 110\u2013113)."},{"key":"9332_CR17","unstructured":"Navarathna, R., Kleinschmidt, T., Dean, D. B., Sridharan, S., & Lucey, P. J. (2011). Can audio-visual speech recognition outperform acoustically enhanced speech recognition in automotive environment? In In Interspeech, (pp. 2241\u20132244)."},{"key":"9332_CR2","doi-asserted-by":"crossref","unstructured":"Potamianos, G., & Neti, C. (2003) Audio-visual speech recognition in challenging environments. In INTERSPEECH (pp. 1293\u20131296).","DOI":"10.21437\/Eurospeech.2003-410"},{"key":"9332_CR21","first-page":"23","volume":"22","author":"G Potamianos","year":"2004","unstructured":"Potamianos, G., Neti, C., Luettin, J., & Matthews, I. (2004). Audio-visual automatic speech recognition: An overview. Issues in Visual and Audio-Visual Speech Processing, 22, 23.","journal-title":"Issues in Visual and Audio-Visual Speech Processing"},{"key":"9332_CR6","doi-asserted-by":"crossref","unstructured":"Potamianos, G., & Lucey, P. (2006). Audio-visual asr from multiple views inside smart rooms. In IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (pp. 35\u201340).","DOI":"10.1109\/MFI.2006.265643"},{"issue":"2","key":"9332_CR3","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1109\/TCYB.2013.2250954","volume":"44","author":"D Stewart","year":"2014","unstructured":"Stewart, D., Seymour, R., Pass, A., & Ming, J. (2014). Robust audio-visual speech recognition under noisy audio-video conditions. IEEE Transactions on Cybernetics, 44(2), 175\u2013184.","journal-title":"IEEE Transactions on Cybernetics"},{"key":"9332_CR19","doi-asserted-by":"crossref","unstructured":"Viola, P., Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, (Vol. 1, pp. 511\u2013518).","DOI":"10.1109\/CVPR.2001.990517"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-016-9332-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-016-9332-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-016-9332-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,16]],"date-time":"2023-08-16T16:05:35Z","timestamp":1692201935000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-016-9332-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,1,23]]},"references-count":22,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,3]]}},"alternative-id":["9332"],"URL":"https:\/\/doi.org\/10.1007\/s10772-016-9332-x","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,1,23]]}}}