{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T20:24:42Z","timestamp":1725913482553},"publisher-location":"Cham","reference-count":14,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319699226"},{"type":"electronic","value":"9783319699233"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-69923-3_62","type":"book-chapter","created":{"date-parts":[[2017,10,19]],"date-time":"2017-10-19T02:14:39Z","timestamp":1508379279000},"page":"575-583","source":"Crossref","is-referenced-by-count":5,"title":["Efficient Audio-Visual Speaker Recognition via Deep Heterogeneous Feature Fusion"],"prefix":"10.1007","author":[{"given":"Yu-Hang","family":"Liu","sequence":"first","affiliation":[]},{"given":"Xin","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Wentao","family":"Fan","sequence":"additional","affiliation":[]},{"given":"Bineng","family":"Zhong","sequence":"additional","affiliation":[]},{"given":"Ji-Xiang","family":"Du","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,10,20]]},"reference":[{"key":"62_CR1","doi-asserted-by":"crossref","unstructured":"Bredin, H., Chollet, G.: Audio-visual speech synchrony measure for talking-face identity verification. In: Processing of IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 233\u2013236 (2007)","DOI":"10.1109\/ICASSP.2007.366215"},{"key":"62_CR2","unstructured":"Cheng, H.T., Chao, Y.H., Yeh, S.L., Chen, C.S.: An efficient approach to multimodal person identity verification by fusing face and voice information. In: Processing of IEEE International Conference on Multimedia and Expo, pp. 542\u2013545, 2005"},{"issue":"3","key":"62_CR3","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1016\/j.jvlc.2009.01.009","volume":"20","author":"W Feng","year":"2009","unstructured":"Feng, W., Xie, L., Zeng, J., Liu, Z.Q.: Audio-visual human recognition using semi-supervised spectral learning and hidden markov models. J. Vis. Lang. Comput. 20(3), 188\u2013195 (2009)","journal-title":"J. Vis. Lang. Comput."},{"key":"62_CR4","doi-asserted-by":"crossref","unstructured":"Geng, J., Liu, X., Cheung, Y.: Audio-visual speaker recognition via multi-modal correlated neural networks. In: IEEE\/wic\/acm International Conference on Web Intelligence Workshops, pp. 123\u2013128 (2016)","DOI":"10.1109\/WIW.2016.043"},{"key":"62_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1007\/11550907_126","volume-title":"Artificial Neural Networks: Formal Models and Their Applications \u2013 ICANN 2005","author":"A Graves","year":"2005","unstructured":"Graves, A., Fern\u00e1ndez, S., Schmidhuber, J.: Bidirectional LSTM networks for improved phoneme classification and recognition. In: Duch, W., Kacprzyk, J., Oja, E., Zadro\u017cny, S. (eds.) ICANN 2005. LNCS, vol. 3697, pp. 799\u2013804. Springer, Heidelberg (2005). doi:\n10.1007\/11550907_126"},{"issue":"9","key":"62_CR6","doi-asserted-by":"crossref","first-page":"1984","DOI":"10.1109\/TIFS.2016.2569061","volume":"11","author":"M Haghighat","year":"2016","unstructured":"Haghighat, M., Abdel-Mottaleb, M., Alhalabi, W.: Discriminant correlation analysis: real-time feature level fusion for multimodal biometric recognition. IEEE Trans. Inf. Forensics Secur. 11(9), 1984\u20131996 (2016)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"62_CR7","doi-asserted-by":"crossref","unstructured":"Hu, Y., Ren, J.S.J., Dai, J., Yuan, C., Xu, L., Wang, W.: Deep multimodal speaker naming. In: Proceedings of Annual ACM International Conference on Multimedia, pp. 1107\u20131110 (2015)","DOI":"10.1145\/2733373.2806293"},{"key":"62_CR8","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceeding of IEEE International Conference on Machine Learning, pp. 448\u2013456 (2015)"},{"key":"62_CR9","unstructured":"Maas, A.L., Hannun, A.Y., Ng, A.Y.: Rectifier nonlinearities improve neural network acoustic models. In: Processing of IEEE International Conference on Machine Learning Workshop, pp. 1\u20136 (2013)"},{"key":"62_CR10","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: Proceedings of IEEE International Conference on Machine Learning, pp. 689\u2013696 (2011)"},{"issue":"4","key":"62_CR11","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1016\/j.specom.2011.11.004","volume":"54","author":"M Sahidullah","year":"2012","unstructured":"Sahidullah, M., Saha, G.: Design, analysis and experimental evaluation of block based transformation in MFCC computation for speaker recognition. Speech Commun. 54(4), 543\u2013565 (2012)","journal-title":"Speech Commun."},{"issue":"6","key":"62_CR12","first-page":"41","volume":"21","author":"M Soltane","year":"2010","unstructured":"Soltane, M., Doghmane, N., Guersi, N.: Face and speech based multi-modal biometric authentication. Process. IEEE Int. J. Adv. Sci. Technol. 21(6), 41\u201356 (2010)","journal-title":"Process. IEEE Int. J. Adv. Sci. Technol."},{"issue":"1","key":"62_CR13","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"issue":"1C2","key":"62_CR14","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1016\/S0925-2312(03)00373-4","volume":"55","author":"AV David S\u00e1nchez","year":"2003","unstructured":"David S\u00e1nchez, A.V.: Advanced support vector machines and kernel methods. Neurocomputing 55(1C2), 5\u201320 (2003)","journal-title":"Neurocomputing"}],"container-title":["Lecture Notes in Computer Science","Biometric Recognition"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-69923-3_62","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,10,19]],"date-time":"2017-10-19T02:34:50Z","timestamp":1508380490000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-69923-3_62"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319699226","9783319699233"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-69923-3_62","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}