{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T14:37:55Z","timestamp":1740148675305,"version":"3.37.3"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2015,5,28]],"date-time":"2015-05-28T00:00:00Z","timestamp":1432771200000},"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":["61403224, 61273268 and 61370034"],"award-info":[{"award-number":["61403224, 61273268 and 61370034"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"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\/s11265-015-1017-1","type":"journal-article","created":{"date-parts":[[2015,5,27]],"date-time":"2015-05-27T04:40:49Z","timestamp":1432701649000},"page":"229-239","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Discriminative Boosting Algorithm for Diversified Front-End Phonotactic Language Recognition"],"prefix":"10.1007","volume":"82","author":[{"given":"Wei-Wei","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Qiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael T.","family":"Johnson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,5,28]]},"reference":[{"issue":"5","key":"1017_CR1","doi-asserted-by":"crossref","first-page":"1136","DOI":"10.1109\/JPROC.2012.2237151","volume":"101","author":"H Li","year":"2013","unstructured":"Li, H., Ma, B., & Lee, K.A. (2013). Spoken language recognition: from fundamentals to practice. Proceedings of the IEEE, 101(5), 1136\u20131159.","journal-title":"Proceedings of the IEEE"},{"issue":"1","key":"1017_CR2","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1109\/TSA.1996.481450","volume":"4","author":"MA Zissman","year":"1996","unstructured":"Zissman, M.A. (1996). Comparison of four approaches to automatic language identification of telephone speech. IEEE Transactions on Speech and Audio Processing, 4(1), 31\u201334.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"1017_CR3","doi-asserted-by":"crossref","unstructured":"Torres-Carrasquillo, P.A., Singer, E., Kohler, M.A., Greene, R.J., Reynolds, D.A., & Deller Jr, J.R. (2002). Approaches to language identification using Gaussian mixture models and shifted delta cepstral features. In INTERSPEECH (pp. 33\u201336).","DOI":"10.21437\/ICSLP.2002-74"},{"key":"1017_CR4","unstructured":"Schwarz, P. (2009). Phoneme recognition based on long temporal context. PhD thesis. Brno University of Technology."},{"issue":"5","key":"1017_CR5","doi-asserted-by":"crossref","first-page":"1029","DOI":"10.1109\/TASL.2008.924150","volume":"16","author":"KC Sim","year":"2008","unstructured":"Sim, K.C., & Li, H. (2008). On acoustic diversification front-end for spoken language identification. IEEE Transactions on Audio, Speech, and Language Processing, 16(5), 1029\u2013 1037.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"1","key":"1017_CR6","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/S1361-8415(01)80004-9","volume":"1","author":"WM Wells","year":"1996","unstructured":"Wells, W.M., Viola, P., Atsumi, H., Nakajima, S., & Kikinis, R. (1996). Multi-modal volume registration by maximization of mutual information. Medical Image Analysis, 1(1), 35\u201351.","journal-title":"Medical Image Analysis"},{"key":"1017_CR7","doi-asserted-by":"crossref","unstructured":"Bahl, L., Brown, P., de Souza, P.V., & Mercer, R. (1986). Maximum mutual information estimation of hidden Markov model parameters for speech recognition. In IEEE International Conference on Acoustics, Speech, and Signal Processing (pp. 49\u201352).","DOI":"10.1109\/ICASSP.1986.1169179"},{"key":"1017_CR8","doi-asserted-by":"crossref","unstructured":"Povey, D., & Woodland, P. C. (2002). Minimum phone error and I-smoothing for improved discriminative training. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (pp. 101\u2013105).","DOI":"10.1109\/ICASSP.2002.1005687"},{"issue":"12","key":"1017_CR9","doi-asserted-by":"crossref","first-page":"3043","DOI":"10.1109\/78.175747","volume":"40","author":"BH Juang","year":"1992","unstructured":"Juang, B.H., & Katagiri, S. (1992). Discriminative learning for minimum error classification [pattern recognition]. IEEE Transactions on Signal Processing, 40(12), 3043\u20133054.","journal-title":"IEEE Transactions on Signal Processing"},{"issue":"2","key":"1017_CR10","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1109\/TASL.2010.2047680","volume":"19","author":"WQ Zhang","year":"2011","unstructured":"Zhang, W.Q., He, L., Deng, Y., Liu, J., & Johnson, M.T. (2011). Time-Frequency Cepstral Features and Heteroscedastic Linear Discriminant Analysis for Language Recognition. IEEE Transactions on Audio, Speech, and Language Processing, 19(2), 266\u2013276.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"1017_CR11","doi-asserted-by":"crossref","unstructured":"Singer, E., Torres-Carrasquillo, P.A., Gleason, T.P., Campbell, W.M., & Reynolds, D.A. (2003). Acoustic, phonetic, and discriminative approaches to automatic language identification. In INTERSPEECH (pp. 1944\u20131948).","DOI":"10.21437\/Eurospeech.2003-417"},{"key":"1017_CR12","unstructured":"Martin, A. F., & Greenberg, C. S. (2010). The 2009 NIST Language Recognition Evaluation. In Odyssey (p. 30)."},{"issue":"1","key":"1017_CR13","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.H. (2007). A vector space modeling approach to spoken language identification. IEEE Transactions on Audio, Speech, and Language Processing, 15(1), 271\u2013284.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"1017_CR14","doi-asserted-by":"crossref","unstructured":"Gauvain, J. L., Messaoudi, A., & Schwenk, H. (2004). Language recognition using phone latices. In INTERSPEECH (pp. 1283\u20131286).","DOI":"10.21437\/Interspeech.2004-28"},{"issue":"1","key":"1017_CR15","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"GE Dahl","year":"2012","unstructured":"Dahl, G.E., Yu, D., Deng, L., & Acero, A. (2012). Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Transactions on Audio, Speech, and Language Processing, 20(1), 30\u201342.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"1017_CR16","unstructured":"Campbell, W. M., Campbell, J. P., Reynolds, D. A., Jones, D. A., & Leek, T. R. (2003). Phonetic speaker recognition with support vector machines. In Advances in Neural Information Processing Systems (pp. 1377\u20131384)."},{"key":"1017_CR17","unstructured":"Matejka, P., Burget, L., Glembek, O., Schwarz, P., Hubeika, V., Fapso, M., & Plchot, O. (2007). BUT system description for NIST LRE 2007. In 2007 NIST Language Recognition Evaluation Workshop (pp. 1\u20135)."},{"key":"1017_CR18","unstructured":"Povey, D. (2005). Discriminative training for large vocabulary speech recognition (Doctoral dissertation, University of Cambridge)."},{"key":"1017_CR19","unstructured":"Jancik, Z., Plchot, O., Brmmer, N., Burget, L., Glembek, O., Hubeika, V., & Cernocky, J. (2010). Data selection and calibration issues in automatic language recognition-investigation with BUT-AGNITIO NIST LRE 2009 system. In Odyssey (pp. 215\u2013221)."},{"key":"1017_CR20","doi-asserted-by":"crossref","unstructured":"Torres-Carrasquillo, P.A., Singer, E., Gleason, T., McCree, A., Reynolds, D.A., Richardson, F., & Sturim, D. (2010). The MITLL NIST LRE 2009 language recognition system. In IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) (pp. 4994\u20134997).","DOI":"10.1109\/ICASSP.2010.5495080"},{"key":"1017_CR21","doi-asserted-by":"crossref","unstructured":"Liu, W.-W., Cai, M., Yuan, H., Xu, J., Liu, J., & Zhang, W.-Q. (2014). DNN-HMM acoustic model for phonotactic language recognition. International Symposium on Chinese Spoken Language Processing(ISCSLP), 148\u2013152.","DOI":"10.1109\/ISCSLP.2014.6936704"},{"key":"1017_CR22","doi-asserted-by":"crossref","unstructured":"Cai, M., Shi, Y., & Liu, J. (2013). Deep maxout neural networks for speech recognition. In IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) (pp. 291\u2013296).","DOI":"10.1109\/ASRU.2013.6707745"},{"key":"1017_CR23","doi-asserted-by":"crossref","unstructured":"Godfrey, J. J., Holliman, E. C., & McDaniel, J. (1992). SWITCHBOARD: Telephone speech corpus for research and development. In EEE International Conference on Acoustics Speech, and Signal Processing (pp. 517\u2013520).","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"1017_CR24","doi-asserted-by":"crossref","unstructured":"Seide, F., Li, G., Chen, X., & Yu, D. (2011). Feature engineering in context-dependent deep neural networks for conversational speech transcription. In IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) (pp. 24\u201329).","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"1017_CR25","unstructured":"Mnih, V. (2009). Cudamat: a CUDA-based matrix class for python. Department of Computer Science, University of Toronto, Tech. Rep. UTML TR."},{"issue":"3","key":"1017_CR26","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1587\/transinf.E94.D.679","volume":"94","author":"Y Deng","year":"2011","unstructured":"Deng, Y., Zhang, W.-Q., Qian, Y.M., & Liu, J. (2011). Language recognition based on acoustic diversified phone recognizers and phonotactic feature fusion. IEICE Transactions on Information and Systems, 94(3), 679\u2013689.","journal-title":"IEICE Transactions on Information and Systems"},{"key":"1017_CR27","unstructured":"Young, S., Evermann, G., Gales, M., Hain, T., Kershaw, D., Liu, X.A., & Woodland, P. (2006). The HTK book (for HTK version 3.4)."},{"key":"1017_CR28","doi-asserted-by":"crossref","unstructured":"Stolcke, A. (2002). SRILM-an extensible language modeling toolkit. In INTERSPEECH.","DOI":"10.21437\/ICSLP.2002-303"},{"key":"1017_CR29","unstructured":"Mikolov, T., Kombrink, S., Deoras, A., Burget, L., & Cernocky, J. (2011). RNNLM-Recurrent neural network language modeling toolkit. In Proceeding of the 2011 ASRU Workshop (pp. 196\u2013201)."},{"key":"1017_CR30","unstructured":"Fan, R.E., Chang, K.W., Hsieh, C.J., Wang, X.R., & Lin, C.J. (2008). LIBLINEAR: A library for large linear classification. The Journal of Machine Learning Research, 1871\u20131874."},{"issue":"1","key":"1017_CR31","first-page":"124","volume":"19","author":"WQ Zhang","year":"2010","unstructured":"Zhang, W.Q., Hou, T., & Liu, J. (2010). Discriminative score fusion for language identification. Chinese Journal of Electronics, 19(1), 124\u2013128.","journal-title":"Chinese Journal of Electronics"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-015-1017-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11265-015-1017-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-015-1017-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,10]],"date-time":"2023-08-10T22:25:06Z","timestamp":1691706306000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11265-015-1017-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,5,28]]},"references-count":31,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2016,2]]}},"alternative-id":["1017"],"URL":"https:\/\/doi.org\/10.1007\/s11265-015-1017-1","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"type":"print","value":"1939-8018"},{"type":"electronic","value":"1939-8115"}],"subject":[],"published":{"date-parts":[[2015,5,28]]}}}