{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T15:19:26Z","timestamp":1743002366580,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319294506"},{"type":"electronic","value":"9783319294513"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"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":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-29451-3_50","type":"book-chapter","created":{"date-parts":[[2016,2,3]],"date-time":"2016-02-03T01:14:44Z","timestamp":1454462084000},"page":"631-641","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Deep Boltzmann Machines for i-Vector Based Audio-Visual Person Identification"],"prefix":"10.1007","author":[{"given":"Mohammad Rafiqul","family":"Alam","sequence":"first","affiliation":[]},{"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[]},{"given":"Roberto","family":"Togneri","sequence":"additional","affiliation":[]},{"given":"Ferdous","family":"Sohel","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,2,4]]},"reference":[{"key":"50_CR1","doi-asserted-by":"crossref","unstructured":"Alam, M.R., Bennamoun, M., Togneri, R., Sohel, F.: An efficient reliability estimation technique for audio-visual person identification. In: 2013 8th IEEE Conference on Industrial Electronics and Applications (ICIEA), pp. 1631\u20131635. IEEE (2013)","DOI":"10.1109\/ICIEA.2013.6566630"},{"key":"50_CR2","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.patrec.2014.10.006","volume":"52","author":"MR Alam","year":"2015","unstructured":"Alam, M.R., Bennamoun, M., Togneri, R., Sohel, F.: A confidence-based late fusion framework for audio-visual biometric identification. Pattern Recogn. Lett. 52, 65\u201371 (2015)","journal-title":"Pattern Recogn. Lett."},{"key":"50_CR3","doi-asserted-by":"crossref","unstructured":"Khoury, E., Vesnicer, B., Franco-Pedroso, J., Violato, R., Boulkcnafet, Z., Mazaira Fernandez, L.M., Diez, M., Kosmala, J., Khemiri, H., Cipr, T., et al.: The 2013 speaker recognition evaluation in mobile environment. In: Proceedings of the 2013 International Conference on Biometrics (ICB), pp. 1\u20138. IEEE (2013)","DOI":"10.1109\/ICB.2013.6613025"},{"key":"50_CR4","doi-asserted-by":"crossref","unstructured":"Gunther, M., Costa-Pazo, A., Ding, C., Boutellaa, E., Chiachia, G., Zhang, H., de Assis Angeloni, M., Struc, V., Khoury, E., Vazquez-Fernandez, E., et al.: The 2013 face recognition evaluation in mobile environment. In: Proceedings of the 2013 International Conference on Biometrics (ICB), pp. 1\u20137. IEEE (2013)","DOI":"10.1109\/ICB.2013.6613024"},{"key":"50_CR5","doi-asserted-by":"crossref","unstructured":"McCool, C., Marcel, S., Hadid, A., Pietikainen, M., Matejka, P., Cernocky, J., Poh, N., Kittler, J., Larcher, A., Levy, C., et al.: Bi-modal person recognition on a mobile phone: using mobile phone data. In: Proceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), pp. 635\u2013640. IEEE (2012)","DOI":"10.1109\/ICMEW.2012.116"},{"issue":"4","key":"50_CR6","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2011","unstructured":"Dehak, N., Kenny, P., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19(4), 788\u2013798 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"4","key":"50_CR7","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1049\/iet-bmt.2012.0024","volume":"1","author":"R Wallace","year":"2012","unstructured":"Wallace, R., McLaren, M.: Total variability modelling for face verification. IET Biometrics 1(4), 188\u2013199 (2012)","journal-title":"IET Biometrics"},{"issue":"12","key":"50_CR8","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1016\/j.imavis.2013.10.001","volume":"32","author":"E Khoury","year":"2014","unstructured":"Khoury, E., El Shafey, L., McCool, C., G\u00fcnther, M., Marcel, S.: Bi-modal biometric authentication on mobile phones in challenging conditions. Image Vis. Comput. 32(12), 1147\u20131160 (2014)","journal-title":"Image Vis. Comput."},{"issue":"6","key":"50_CR9","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., Deng, L., Yu, D., Dahl, G.E., Mohamed, A.R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T.N., et al.: Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Sig. Process. Mag. 29(6), 82\u201397 (2012)","journal-title":"IEEE Sig. Process. Mag."},{"issue":"1","key":"50_CR10","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/MSP.2010.939038","volume":"28","author":"D Yu","year":"2011","unstructured":"Yu, D., Deng, L.: Deep learning and its applications to signal and information processing [exploratory dsp]. IEEE Sig. Process. Mag. 28(1), 145\u2013154 (2011)","journal-title":"IEEE Sig. Process. Mag."},{"issue":"5786","key":"50_CR11","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504\u2013507 (2006)","journal-title":"Science"},{"key":"50_CR12","doi-asserted-by":"crossref","unstructured":"Ghahabi, O., Hernando, J.: Deep belief networks for i-vector based speaker recognition. In: Proceedings of the 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1700\u20131704. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6853888"},{"key":"50_CR13","unstructured":"Vasilakakis, V., Cumani, S., Laface, P.: Speaker recognition by means of deep belief networks. In: Proceedings of the Biometric Technologies in Forensic Science (BTFS) (2013)"},{"key":"50_CR14","unstructured":"Br\u00fcmmer, N., De Villiers, E.: The speaker partitioning problem. In: Odyssey, p. 34 (2010)"},{"key":"50_CR15","unstructured":"Kenny, P.: Bayesian speaker verification with heavy-tailed priors. In: Odyssey, p. 14 (2010)"},{"key":"50_CR16","unstructured":"Salakhutdinov, R., Hinton, G.E.: Deep boltzmann machines. In: Proceedings of the 2009 International Conference on Artificial Intelligence and Statistics, pp. 448\u2013455 (2009)"},{"key":"50_CR17","doi-asserted-by":"crossref","unstructured":"You, Z., Wang, X., Xu, B.: Investigation of deep boltzmann machines for phone recognition. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7600\u20137603. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6639141"},{"key":"50_CR18","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Salakhutdinov, R., Chang, H.A., Glass, J.: Resource configurable spoken query detection using deep boltzmann machines. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5161\u20135164. IEEE (2012)","DOI":"10.1109\/ICASSP.2012.6289082"},{"key":"50_CR19","unstructured":"Srivastava, N., Salakhutdinov, R.: Multimodal learning with deep boltzmann machines. In: Advances in Neural Information Processing Systems, pp. 2222\u20132230 (2012)"},{"key":"50_CR20","unstructured":"Senoussaoui, M., Dehak, N., Kenny, P., Dehak, R., Dumouchel, P.: First attempt of boltzmann machines for speaker verification. In: Proceedings of the Odyssey 2012-The Speaker and Language Recognition Workshop (2012)"},{"key":"50_CR21","unstructured":"Stafylakis, T., Kenny, P., Senoussaoui, M., Dumouchel, P.: Preliminary investigation of boltzmann machine classifiers for speaker recognition. In: Proceedings of the 2012 Odyssey Speaker and Language Recognition Workshop (2012)"},{"key":"50_CR22","unstructured":"Salakhutdinov, R.: Learning deep boltzmann machines using adaptive mcmc. In: Proceedings of the 27th International Conference on Machine Learning (ICML), pp. 943\u2013950 (2010)"},{"issue":"8","key":"50_CR23","doi-asserted-by":"publisher","first-page":"1967","DOI":"10.1162\/NECO_a_00311","volume":"24","author":"R Salakhutdinov","year":"2012","unstructured":"Salakhutdinov, R., Hinton, G.: An efficient learning procedure for deep boltzmann machines. Neural Comput. 24(8), 1967\u20132006 (2012)","journal-title":"Neural Comput."},{"key":"50_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1007\/978-3-642-40728-4_14","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2013","author":"KH Cho","year":"2013","unstructured":"Cho, K.H., Raiko, T., Ilin, A., Karhunen, J.: A two-stage pretraining algorithm for deep boltzmann machines. In: Mladenov, V., Koprinkova-Hristova, P., Palm, G., Villa, A.E.P., Appollini, B., Kasabov, N. (eds.) ICANN 2013. LNCS, vol. 8131, pp. 106\u2013113. Springer, Heidelberg (2013)"},{"issue":"1","key":"50_CR25","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.csl.2007.05.003","volume":"22","author":"R Vogt","year":"2008","unstructured":"Vogt, R., Sridharan, S.: Explicit modelling of session variability for speaker verification. Comput. Speech Lang. 22(1), 17\u201338 (2008)","journal-title":"Comput. Speech Lang."},{"issue":"4","key":"50_CR26","doi-asserted-by":"publisher","first-page":"1435","DOI":"10.1109\/TASL.2006.881693","volume":"15","author":"P Kenny","year":"2007","unstructured":"Kenny, P., Boulianne, G., Ouellet, P., Dumouchel, P.: Joint factor analysis versus eigenchannels in speaker recognition. IEEE Trans. Audio Speech Lang. Process. 15(4), 1435\u20131447 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"50_CR27","unstructured":"Brookes, M., et al.: Voicebox: Speech processing toolbox for matlab. Software (1997). \n                      http:\/\/www.ee.ic.ac.uk\/hp\/staff\/dmb\/voicebox\/voicebox.html\n                      \n                    . March 2011"},{"issue":"6","key":"50_CR28","doi-asserted-by":"publisher","first-page":"1635","DOI":"10.1109\/TIP.2010.2042645","volume":"19","author":"X Tan","year":"2010","unstructured":"Tan, X., Triggs, B.: Enhanced local texture feature sets for face recognition under difficult lighting conditions. IEEE Trans. Image Process. 19(6), 1635\u20131650 (2010)","journal-title":"IEEE Trans. Image Process."},{"issue":"14","key":"50_CR29","doi-asserted-by":"publisher","first-page":"2409","DOI":"10.1016\/S0167-8655(03)00070-9","volume":"24","author":"C Sanderson","year":"2003","unstructured":"Sanderson, C., Paliwal, K.K.: Fast features for face authentication under illumination direction changes. Pattern Recog. Lett. 24(14), 2409\u20132419 (2003)","journal-title":"Pattern Recog. Lett."},{"key":"50_CR30","unstructured":"Sadjadi, S.O., Slaney, M., Heck, L.: MSR identity toolbox v1. 0: A matlab toolbox for speaker recognition research. In: Speech and Language Processing Technical Committee Newsletter (2013)"},{"key":"50_CR31","unstructured":"Cho, K.: (2013). \n                      https:\/\/github.com\/kyunghyuncho\/deepmat"},{"key":"50_CR32","unstructured":"Cho, K., Raiko, T., Ihler, A.T.: Enhanced gradient and adaptive learning rate for training restricted boltzmann machines. In: Proceedings of the 28th International Conference on Machine Learning (ICML), pp. 105\u2013112 (2011)"}],"container-title":["Lecture Notes in Computer Science","Image and Video Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-29451-3_50","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,2]],"date-time":"2020-02-02T20:07:30Z","timestamp":1580674050000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-29451-3_50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319294506","9783319294513"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-29451-3_50","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"4 February 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}