{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T06:30:31Z","timestamp":1722580231641},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2015,7,2]],"date-time":"2015-07-02T00:00:00Z","timestamp":1435795200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61401524"],"award-info":[{"award-number":["61401524"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"crossref","award":["2014A030313123"],"award-info":[{"award-number":["2014A030313123"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"crossref"}]},{"name":"SYSU-CMU Shunde International Joint Research Institute","award":["20140302"],"award-info":[{"award-number":["20140302"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Sign Process Syst"],"published-print":{"date-parts":[[2016,2]]},"DOI":"10.1007\/s11265-015-1019-z","type":"journal-article","created":{"date-parts":[[2015,7,1]],"date-time":"2015-07-01T02:06:59Z","timestamp":1435716419000},"page":"207-215","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Generalized I-vector Representation with Phonetic Tokenizations and Tandem Features for both Text Independent and Text Dependent Speaker Verification"],"prefix":"10.1007","volume":"82","author":[{"given":"Ming","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weicheng","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,7,2]]},"reference":[{"issue":"5","key":"1019_CR1","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1109\/LSP.2006.870086","volume":"13","author":"W Campbell","year":"2006","unstructured":"Campbell, W., Sturim, D., & Reynolds, D. (2006). Support vector machines using gmm supervectors for speaker verification. IEEE Signal Processing Letters, 13(5), 308\u2013311.","journal-title":"IEEE Signal Processing Letters"},{"key":"1019_CR2","doi-asserted-by":"crossref","unstructured":"Cumani, S., Brummer, N., Burget, L., & Laface, P. (2011). Fast discriminative speaker verification in the i-vector space. In Proceedings ICASSP (pp. 4852\u20134855): IEEE.","DOI":"10.1109\/ICASSP.2011.5947442"},{"issue":"4","key":"1019_CR3","doi-asserted-by":"crossref","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. (2011). Front-end factor analysis for speaker verification. IEEE Transactions on Audio, Speech, and Language Processing, 19(4), 788\u2013798.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"1019_CR4","doi-asserted-by":"crossref","unstructured":"Dehak, N., Torres-Carrasquillo, P., Reynolds, D., & Dehak, R. (2011). Language recognition via i-vectors and dimensionality reduction. In Proceedings INTERSPEECH (pp. 857\u2013860).","DOI":"10.21437\/Interspeech.2011-328"},{"key":"1019_CR5","doi-asserted-by":"crossref","unstructured":"D\u2019Haro, L.F., Cordoba, R., Salamea, C., & Echeverry, J.D. (2014). Extended phone log-likelihood ratio features and acoustic-based i-vectors for language recognition. In Proceedings ICASSP (pp. 5379\u20135383): IEEE.","DOI":"10.1109\/ICASSP.2014.6854623"},{"key":"1019_CR6","doi-asserted-by":"crossref","unstructured":"Ellis, D.P., Singh, R., & Sivadas, S. (2001). Tandem acoustic modeling in large-vocabulary recognition, (Vol. 1 pp. 517\u2013520): Proceedings ICASSP.","DOI":"10.1109\/ICASSP.2001.940881"},{"key":"1019_CR7","unstructured":"Hatch, A., Kajarekar, S., & Stolcke, A. (2006). Within-class covariance normalization for SVM-based speaker recognition, (Vol. 4 pp. 1471\u20131474): Proceedings INTERSPEECH."},{"key":"1019_CR8","doi-asserted-by":"crossref","unstructured":"H\u00e9bert, M. (2008). Text-dependent speaker recognition. Springer Handbook of Speech Processing, 743\u2013762.","DOI":"10.1007\/978-3-540-49127-9_37"},{"key":"1019_CR9","doi-asserted-by":"crossref","unstructured":"Hermansky, H., Ellis, D.P., & Sharma, S. (2000). Tandem connectionist feature extraction for conventional hmm systems. In Proceedings ICASSP, (Vol. 3 pp. 1635\u20131638).","DOI":"10.1109\/ICASSP.2000.862024"},{"issue":"3","key":"1019_CR10","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1109\/TSA.2004.840940","volume":"13","author":"P Kenny","year":"2005","unstructured":"Kenny, P., Boulianne, G., & Dumouchel, P. (2005). Eigenvoice modeling with sparse training data. IEEE Transactions on Speech and Audio Processing, 13(3), 345\u2013354.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"1019_CR11","doi-asserted-by":"crossref","unstructured":"Kenny, P., Stafylakis, T., Ouellet, P., & Alam, M.J. (2014). Jfa-based front ends for speaker recognition. In Proceedings ICASSP (pp. 1724\u20131728).","DOI":"10.1109\/ICASSP.2014.6853889"},{"key":"1019_CR12","doi-asserted-by":"crossref","unstructured":"Larcher, A., Lee, K.A., Ma, B., & Li, H. (2014). Imposture classification for text-dependent speaker verification. In Proceedings ICASSP (pp. 739\u2013743).","DOI":"10.1109\/ICASSP.2014.6853694"},{"key":"1019_CR13","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.specom.2014.03.001","volume":"60","author":"A Larcher","year":"2014","unstructured":"Larcher, A., Lee, K.A., Ma, B., & Li, H. (2014). Text-dependent speaker verification: Classifiers, databases and rsr2015. Speech Communication, 60, 56\u201377.","journal-title":"Speech Communication"},{"key":"1019_CR14","doi-asserted-by":"crossref","unstructured":"Lei, Y., Scheffer, N., Ferrer, L., & McLaren, M. (2014). A novel scheme for speaker recognition using a phonetically-aware deep neural network. In Proceedings ICASSP.","DOI":"10.1109\/ICASSP.2014.6853887"},{"issue":"1","key":"1019_CR15","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1109\/TASL.2006.876860","volume":"15","author":"H Li","year":"2007","unstructured":"Li, H., Ma, B., & Lee, C. (2007). A vector space modeling approach to spoken language identification. IEEE Transactions on Audio. Speech, and Language Processing, 15(1), 271\u2013284.","journal-title":"Speech, and Language Processing"},{"key":"1019_CR16","doi-asserted-by":"crossref","unstructured":"Li, M., & Narayanan, S. (2014). Simplified supervised i-vector modeling with application to robust and efficient language identification and speaker verification: Computer speech and language.","DOI":"10.1016\/j.csl.2014.02.004"},{"key":"1019_CR17","doi-asserted-by":"crossref","unstructured":"Li, M., Tsiartas, A., Van Segbroeck, M., & Narayanan, S.S. (2013). Speaker verification using simplified and supervised i-vector modeling. In Proceedings ICASSP (pp. 7199\u20137203): IEEE.","DOI":"10.1109\/ICASSP.2013.6639060"},{"key":"1019_CR18","doi-asserted-by":"crossref","unstructured":"Li, M., Zhang, X., Yan, Y., & Narayanan, S. (2011). Speaker verification using sparse representations on total variability i-vectors. In Proceedings INTERSPEECH (pp. 4548\u20134551).","DOI":"10.21437\/Interspeech.2011-149"},{"key":"1019_CR19","doi-asserted-by":"crossref","unstructured":"Matejka, P., Glembek, O., Castaldo, F., Alam, M., Plchot, O., Kenny, P., Burget, L., & Cernocky, J. (2011). Full-covariance ubm and heavy-tailed plda in i-vector speaker verification. In Proceedings ICASSP (pp. 4828\u20134831).","DOI":"10.1109\/ICASSP.2011.5947436"},{"key":"1019_CR20","unstructured":"(2010). NIST: The NIST 2010 Speaker Recognition Evaluation Plan. www.itl.nist.gov\/iad\/mig\/tests\/spk\/2010\/index.html ."},{"key":"1019_CR21","doi-asserted-by":"crossref","unstructured":"Novoselov, S., Pekhovsky, T., Shulipa, A., & Sholokhov, A. (2014). Text-dependent gmm-jfa system for password based speaker verification. In Proceedings ICASSP (pp. 729\u2013733).","DOI":"10.1109\/ICASSP.2014.6853692"},{"key":"1019_CR22","doi-asserted-by":"crossref","unstructured":"Pinto, J., Garimella, S., Hermansky, H., Bourlard, H., & et al. (2011). Analysis of mlp-based hierarchical phoneme posterior probability estimator. IEEE Transactions on Audio, Speech, and Language Processing, 19(2), 225\u2013241.","DOI":"10.1109\/TASL.2010.2045943"},{"key":"1019_CR23","doi-asserted-by":"crossref","unstructured":"Prince, S., & Elder, J. (2007). Probabilistic linear discriminant analysis for inferences about identity (pp. 1\u20138): Proceedings ICCV.","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"1019_CR24","doi-asserted-by":"crossref","unstructured":"Schwarz, P., Matejka, P., & Cernocky, J. (2006). Hierarchical structures of neural networks for phoneme. In Proc. ICASSP. Software available at http:\/\/speech.fit.vutbr.cz\/software\/phoneme-recognizer-based-long-temporal-context (pp. 325\u2013328).","DOI":"10.1109\/ICASSP.2006.1660023"},{"key":"1019_CR25","doi-asserted-by":"crossref","unstructured":"Stolcke, A., & et al. (2002). Srilm-an extensible language modeling toolkit. In Proceedings INTERSPEECH.","DOI":"10.21437\/ICSLP.2002-303"},{"key":"1019_CR26","doi-asserted-by":"crossref","unstructured":"Variani, E., Lei, X., McDermott, E., Moreno, I.L., & Gonzalez-Dominguez, J. (2014). Deep neural networks for small footprint text-dependent speaker verification. In Proceedings ICASSP (pp. 4080\u20134084).","DOI":"10.1109\/ICASSP.2014.6854363"},{"issue":"1","key":"1019_CR27","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1109\/LSP.2012.2227312","volume":"20","author":"H Wang","year":"2013","unstructured":"Wang, H., Leung, C.C., Lee, T., Ma, B., & Li, H. (2013). Shifted-delta mlp features for spoken language recognition. IEEE Signal Processing Letters, 20(1), 15\u201318.","journal-title":"IEEE Signal Processing Letters"},{"key":"1019_CR28","unstructured":"Young, S., Evermann, G., Kershaw, D., Moore, G., Odell, J., Ollason, D., Valtchev, V., & Woodland, P. (1997). The HTK book, vol. 2: Entropic Cambridge Research Laboratory Cambridge."},{"key":"1019_CR29","unstructured":"Zhu, Q., Stolcke, A., Chen, B.Y., & Morgan, N. (2005). Using mlp features in sris conversational speech recognition system. In Proc. INTERSPEECH."}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-015-1019-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11265-015-1019-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-015-1019-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T22:25:22Z","timestamp":1691792722000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11265-015-1019-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7,2]]},"references-count":29,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2016,2]]}},"alternative-id":["1019"],"URL":"https:\/\/doi.org\/10.1007\/s11265-015-1019-z","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"value":"1939-8018","type":"print"},{"value":"1939-8115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,7,2]]}}}