{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T14:17:53Z","timestamp":1761401873333},"reference-count":18,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2017]]},"DOI":"10.1587\/transinf.2016edl8106","type":"journal-article","created":{"date-parts":[[2016,12,31]],"date-time":"2016-12-31T22:21:58Z","timestamp":1483222918000},"page":"215-219","source":"Crossref","is-referenced-by-count":3,"title":["Deep Nonlinear Metric Learning for Speaker Verification in the I-Vector Space"],"prefix":"10.1587","volume":"E100.D","author":[{"given":"Yong","family":"FENG","sequence":"first","affiliation":[{"name":"School of Automation, Chongqing University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingyu","family":"XIONG","sequence":"additional","affiliation":[{"name":"School of Automation, Chongqing University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiren","family":"SHI","sequence":"additional","affiliation":[{"name":"School of Automation, Chongqing University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","unstructured":"[1] A. Kabir and S.M.M. Ahsan, \u201cVector quantization in text dependent automatic speaker recognition using mel-frequency cepstrum coefficient [C],\u201d Proc. 6th WSEAS International Conference on Circuits, Systems, Electronics, Control and Signal Processing, Cairo, Egypt, 2007."},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] D.A. Reynolds, \u201cSpeaker identification and verification using Gaussian mixture speaker models [J],\u201d Speech communication, vol.17, no.1-2, pp.91-108, 1995.","DOI":"10.1016\/0167-6393(95)00009-D"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] W.M. Campbell, D.E. Sturim, and D.A. Reynolds, \u201cSupport vector machines using GMM supervectors for speaker verification [J],\u201d IEEE Signal Processing Letters, vol.13, no.5, pp.308-311, 2006.","DOI":"10.1109\/LSP.2006.870086"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] P. Kenny, G. Boulianne, P. Ouellet, and P. Dumouchel, \u201cSpeaker and session variability in GMM-based speaker verification [J],\u201d IEEE Transactions on Audio, Speech and Language Processing, vol.15, no.4, pp.1448-1460, 2007.","DOI":"10.1109\/TASL.2007.894527"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] D.N. Dehak, R. Dehak, P. Kenny, et al., \u201cSupport vector machines versus fast scoring in the low-dimensional total variability space for speaker verification [C],\u201d Conference of the International Speech Communication Association, 2009.","DOI":"10.21437\/Interspeech.2009-385"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] A.O. Hatch, S.S. Kajarekar, and A. Stolcke, \u201cWithin-class covariance normalization for SVM-based speaker recognition,\u201d INTERSPEECH, 2006.","DOI":"10.21437\/Interspeech.2006-183"},{"key":"7","unstructured":"[7] A. Solomonoff, C. Quillen, and W.M. Campbell, \u201cChannel compensation for SVM speaker recognition,\u201d Proc. Odyssey, Speaker Language Recognition Workshop 2004, pp.57-62, 2004."},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] N. Dehak, P.J. Kenny, R. Dehak, P. Ouellet, and P. Dumouchel, \u201cFront-end factor analysis for speaker verification,\u201d IEEE Transactions on Audio, Speech and Language Processing, vol.19, no.4, pp.788-798, 2011.","DOI":"10.1109\/TASL.2010.2064307"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] S. Ioffe, \u201cProbabilistic linear discriminant analysis,\u201d Computer Vision ECCV, Springer Berlin Heidelberg, pp.531-542, 2006.","DOI":"10.1007\/11744085_41"},{"key":"10","unstructured":"[10] L. Yang and R. Jin, \u201cDistance metric learning: A comprehensive survey,\u201d Michigan State University, May 2006."},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] D. Yu and M. Seltzer, \u201cImproved Bottleneck Features Using Pretrained Deep Neural Networks,\u201d Proc. Interspeech, 2011.","DOI":"10.21437\/Interspeech.2011-91"},{"key":"12","unstructured":"[12] T. Yamada, L. Wang, and A. Kai, \u201cImprovement of distant-talking speaker identification using bottleneck features of DNN,\u201d Proc. Interspeech, pp.3361-3364, 2013."},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] Z. Zhang, L. Wang, A. Kai, T. Yamada, W. Li, and M. Iwahashi, \u201cDeep neural network-based bottleneck feature and denoising autoencoder-based dereverberation for distant-talking speaker identification,\u201d Eurasip Journal on Audio, Music and Speech Processing, 2015:12, 2015.","DOI":"10.1186\/s13636-015-0056-7"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] F. Richardson, D. Reynolds, and N. Dehak, \u201cDeep Neural Network Approaches to Speaker and Language Recognition,\u201d Signal Processing Letters, IEEE, vol.22, no.10, pp.1671-1675, 2015.","DOI":"10.1109\/LSP.2015.2420092"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] A. Fischer and C. Igel, \u201cAn introduction to restricted Boltzmann machines,\u201d L. Alvarez et al. (Eds.): CIARP 2012, LNCS 7441, pp.14-36, 2012.","DOI":"10.1007\/978-3-642-33275-3_2"},{"key":"16","unstructured":"[16] E.P. Xing, A.Y. Ng, M.I. Jordan, et al., \u201cDistance metric learning with application to clustering with side-information [J],\u201d Advances in Neural Information Processing Systems, pp.505-512, 2003."},{"key":"17","unstructured":"[17] NIST, The NIST year 2008 speaker recognition evaluation plan, Online: http:\/\/www.itl.nist.gov\/iad\/mig\/tests\/sre\/2008\/sre08evalplanrelease4.pdf, 2008."},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] H.V. Nguyen and L. Bai, \u201cCosine Similarity Metric Learning for Face Verification [C],\u201d Computer Vision-ACCV 2010, Asian Conference on Computer Vision, Queenstown, New Zealand, pp.709-720, Nov. 2010.","DOI":"10.1007\/978-3-642-19309-5_55"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E100.D\/1\/E100.D_2016EDL8106\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,20]],"date-time":"2022-07-20T10:34:53Z","timestamp":1658313293000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E100.D\/1\/E100.D_2016EDL8106\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"references-count":18,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2016edl8106","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]}}}