{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T09:05:56Z","timestamp":1744275956865,"version":"3.37.3"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2017,5,30]],"date-time":"2017-05-30T00:00:00Z","timestamp":1496102400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["Erasmus Mundus Mobility for Life Project"],"award-info":[{"award-number":["Erasmus Mundus Mobility for Life Project"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Wireless Pers Commun"],"published-print":{"date-parts":[[2017,11]]},"DOI":"10.1007\/s11277-017-4544-1","type":"journal-article","created":{"date-parts":[[2017,5,30]],"date-time":"2017-05-30T16:02:36Z","timestamp":1496160156000},"page":"933-950","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Frame Selection for Robust Speaker Identification: A Hybrid Approach"],"prefix":"10.1007","volume":"97","author":[{"given":"Swati","family":"Prasad","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng-Hua","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ramjee","family":"Prasad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,5,30]]},"reference":[{"key":"4544_CR1","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1109\/PROC.1976.10155","volume":"64","author":"BS Atal","year":"1976","unstructured":"Atal, B. S. (1976). Automatic recognition of speakers from their voices. Proceedings of the IEEE, 64, 460\u2013475.","journal-title":"Proceedings of the IEEE"},{"key":"4544_CR2","doi-asserted-by":"crossref","first-page":"1651","DOI":"10.1109\/PROC.1985.13345","volume":"73","author":"GR Doddington","year":"1985","unstructured":"Doddington, G. R. (1985). Speaker recognition\u2014identifying people by their voices. Proceedings of the IEEE, 73, 1651\u20131664.","journal-title":"Proceedings of the IEEE"},{"issue":"9","key":"4544_CR3","doi-asserted-by":"crossref","first-page":"1437","DOI":"10.1109\/5.628714","volume":"85","author":"JP Campbel Jr","year":"1997","unstructured":"Campbel, J. P, Jr. (1997). Speaker recognition: A tutorial. Proceedings of the IEEE, 85(9), 1437\u20131462.","journal-title":"Proceedings of the IEEE"},{"issue":"1","key":"4544_CR4","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.specom.2009.08.009","volume":"52","author":"T Kinnunen","year":"2010","unstructured":"Kinnunen, T., & Li, H. (2010). An overview of text-independent speaker recognition: From features to supervectors. Speech Communications, 52(1), 12\u201340.","journal-title":"Speech Communications"},{"key":"4544_CR5","doi-asserted-by":"crossref","first-page":"5871","DOI":"10.1109\/79.536825","volume":"13","author":"RJ Mammone","year":"1996","unstructured":"Mammone, R. J., Zhang, X., & Ramachandran, R. P. (1996). Robust speaker recognition\u2013a feature based approach. IEEE Signal Processing Magazine, 13, 5871.","journal-title":"IEEE Signal Processing Magazine"},{"issue":"2","key":"4544_CR6","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1109\/MCAS.2011.941079","volume":"11","author":"R Togneri","year":"2011","unstructured":"Togneri, R., & Pullela, D. (2011). An overview of speaker identification: Accuracy and robustness issues. IEEE Circuits Systems Magazine, 11(2), 23\u201361.","journal-title":"IEEE Circuits Systems Magazine"},{"issue":"4","key":"4544_CR7","doi-asserted-by":"crossref","first-page":"836","DOI":"10.1109\/TASLP.2014.2308398","volume":"22","author":"X Zhao","year":"2014","unstructured":"Zhao, X., Wang, Y., & Wang, D. L. (2014). Robust speaker identification in noisy and reverberant conditions. IEEE\/ACM Transactions on Audio, Speech and Language Processing, 22(4), 836\u2013845.","journal-title":"IEEE\/ACM Transactions on Audio, Speech and Language Processing"},{"issue":"7","key":"4544_CR8","doi-asserted-by":"crossref","first-page":"1990","DOI":"10.1109\/TASL.2012.2191960","volume":"20","author":"T Kinnunen","year":"2012","unstructured":"Kinnunen, T., Saeidi, R., Sedlak, F., Lee, K. A., Sandberg, J., Hansson-Sandsten, M., et al. (2012). Low-variance multitaper MFCC features: A case study in robust speaker verification. IEEE\/ACM Transactions on Audio, Speech and Language Processing, 20(7), 1990\u20132001.","journal-title":"IEEE\/ACM Transactions on Audio, Speech and Language Processing"},{"key":"4544_CR9","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1016\/j.specom.2012.08.007","volume":"55","author":"MJ Alam","year":"2013","unstructured":"Alam, M. J., Kinnunen, T., Kenny, P., Ouellet, P., & O\u2019Shaughnessy, D. (2013). Multitaper MFCC and PLP features for speaker verification using i-vectors. Speech Communications, 55, 237\u2013251.","journal-title":"Speech Communications"},{"key":"4544_CR10","doi-asserted-by":"crossref","unstructured":"Sadjadi, S. O., Hasan, T., & Hansen, J. H. L. (2012). Mean hilbert envelope coefficients (MHEC) for robust speaker recognition. In Proceedings of Interspeech (pp. 1696\u20131699).","DOI":"10.21437\/Interspeech.2012-464"},{"issue":"6","key":"4544_CR11","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1109\/89.397090","volume":"3","author":"Y Ephraim","year":"1995","unstructured":"Ephraim, Y., & Van Trees, H. (1995). A signal subspace approach for speech enhancement. IEEE\/ACM Transactions on Audio, Speech and Language Processing, 3(6), 251\u2013266.","journal-title":"IEEE\/ACM Transactions on Audio, Speech and Language Processing"},{"key":"4544_CR12","unstructured":"Brajevic, Z., & Petosic, A. (2012). Signal denoising using STFT with Bayes prediction and Ephraim\u2013Malah estimation. In Proceedings of the 54th international symposium ELMAR (pp. 183\u2013186)."},{"key":"4544_CR13","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1016\/j.dsp.2014.06.007","volume":"33","author":"SM Govindan","year":"2014","unstructured":"Govindan, S. M., Duraisamy, P., & Yuan, X. (2014). Adaptive wavelet shrinkage for noise robust speaker recognition. Digital Signal Processing, 33, 180\u2013190.","journal-title":"Digital Signal Processing"},{"issue":"3","key":"4544_CR14","doi-asserted-by":"crossref","first-page":"1684","DOI":"10.1109\/TCE.2010.5606313","volume":"56","author":"K Kim","year":"2010","unstructured":"Kim, K., & Kim, M. Y. (2010). Robust speaker recognition against background noise in an enhanced multicondition domain. IEEE Transactions on Consumer Electronics, 56(3), 1684\u20131688.","journal-title":"IEEE Transactions on Consumer Electronics"},{"issue":"11","key":"4544_CR15","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1109\/LSP.2011.2169453","volume":"18","author":"L Zao","year":"2011","unstructured":"Zao, L., & Coelho, R. (2011). Colored noise based multicondition training for robust speaker identification. IEEE Signal Processing Letters, 18(11), 675\u2013678.","journal-title":"IEEE Signal Processing Letters"},{"issue":"12","key":"4544_CR16","doi-asserted-by":"crossref","first-page":"1951","DOI":"10.1109\/TASLP.2014.2355821","volume":"22","author":"A Venturini","year":"2014","unstructured":"Venturini, A., Zao, L., & Coelho, R. (2014). On speech features fusion, integration Gaussian modeling and multi-style training for noise robust speaker classification. IEEE\/ACM Transactions on Audio, Speech and Language Processing, 22(12), 1951\u20131964.","journal-title":"IEEE\/ACM Transactions on Audio, Speech and Language Processing"},{"issue":"4","key":"4544_CR17","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. J., Dehak, R., Dumouchel, P., & Ouellet, P. (2011). Front-end factor analysis for speaker verification. IEEE\/ACM Transactions on Audio, Speech and Language Processing, 19(4), 788\u2013798.","journal-title":"IEEE\/ACM Transactions on Audio, Speech and Language Processing"},{"key":"4544_CR18","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.patcog.2005.08.004","volume":"39","author":"DJ Mashao","year":"2006","unstructured":"Mashao, D. J., & Skosan, M. (2006). Combining classifier decisions for robust speaker identification. Pattern Recognition, 39, 147\u2013155.","journal-title":"Pattern Recognition"},{"issue":"1","key":"4544_CR19","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1109\/89.365379","volume":"3","author":"DA Reynolds","year":"1995","unstructured":"Reynolds, D. A., & Rose, R. C. (1995). Robust text-independent speaker identification using Gaussian mixture models. IEEE\/ACM Transactions on Audio, Speech and Language Processing, 3(1), 72\u201383.","journal-title":"IEEE\/ACM Transactions on Audio, Speech and Language Processing"},{"key":"4544_CR20","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/j.csl.2013.07.003","volume":"28","author":"M-W Mak","year":"2014","unstructured":"Mak, M.-W., & Yu, H.-B. (2014). A study of voice activity detection techniques for NIST speaker recognition evaluations. Computer Speech and Language, 28, 295\u2013313.","journal-title":"Computer Speech and Language"},{"issue":"4","key":"4544_CR21","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1049\/iet-spr.2011.0109","volume":"6","author":"S Deng","year":"2012","unstructured":"Deng, S., & Han, J. (2012). Likelihood ratio sign test for voice activity detection. IET Signal Processing, 6(4), 306\u2013312.","journal-title":"IET Signal Processing"},{"issue":"6","key":"4544_CR22","doi-asserted-by":"crossref","first-page":"1332","DOI":"10.1109\/TASL.2009.2033631","volume":"18","author":"C-S Jung","year":"2010","unstructured":"Jung, C.-S., Kim, M. Y., & Kang, H.-G. (2010). Selecting feature frames for automatic speaker recognition using mutual information. IEEE\/ACM Transactions on Audio, Speech and Language Processing, 18(6), 1332\u20131340.","journal-title":"IEEE\/ACM Transactions on Audio, Speech and Language Processing"},{"key":"4544_CR23","doi-asserted-by":"crossref","unstructured":"Fujihara, H., Kitahara, T., Goto, M., Komatani, K., Ogata, T. & Okuno, H. G. (2006). Speaker identification under noisy environment by using harmonic structure extraction and reliable frame weighting. In Proceedings of interspeech (pp. 1459\u20131462).","DOI":"10.21437\/Interspeech.2006-180"},{"issue":"5","key":"4544_CR24","doi-asserted-by":"crossref","first-page":"798","DOI":"10.1109\/JSTSP.2010.2057192","volume":"4","author":"Z-H Tan","year":"2010","unstructured":"Tan, Z.-H., & Lindberg, B. (2010). Low complexity frame rate analysis for speech recognition and voice activity detection. IEEE Journal of Selected Topics in Signal Processing, 4(5), 798\u2013807.","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"4544_CR25","doi-asserted-by":"crossref","first-page":"2139","DOI":"10.1016\/j.compeleceng.2014.09.002","volume":"40","author":"Z-H Tan","year":"2014","unstructured":"Tan, Z.-H., & Kraljevski, I. (2014). Joint variable frame rate and length analysis for speech recognition under adverse conditions. Computers and Electrical Engineering, 40, 2139\u20132149.","journal-title":"Computers and Electrical Engineering"},{"issue":"1","key":"4544_CR26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/97.736233","volume":"6","author":"J Sohn","year":"1999","unstructured":"Sohn, J., Kim, N. S., & Sung, W. (1999). A statistical model based voice activity detection. IEEE Signal Processing Letters, 6(1), 1\u20133.","journal-title":"IEEE Signal Processing Letters"},{"key":"4544_CR27","unstructured":"Hirsch, H. G. & Pearce, D. (2000). The AURORA experimental framework for the performance evaluation of speech recognition systems under noisy conditions. In Proceedings of ISCA ITRW ASR."},{"key":"4544_CR28","doi-asserted-by":"crossref","unstructured":"Campbel, J. P. Jr. (1995). Testing with YOHO cd-rom verification corpus. In Proceedings of IEEE international conference on acoustics, speech, and signal processing (pp. 341\u2013344).","DOI":"10.1109\/ICASSP.1995.479543"},{"key":"4544_CR29","doi-asserted-by":"crossref","unstructured":"M-Guarasa, J., Ordonez, J., Montero, J. M., Ferreiros, J., Cordoba, R., & Haro, L. F. D. (2003). Revisiting scenarios and methods for variable frame rate analysis in automatic speech recognition. In Proceedings of Eurospeech.","DOI":"10.21437\/Eurospeech.2003-499"},{"key":"4544_CR30","unstructured":"Zhu, Q. & Alwan, A. (2000). On the use of variable frame rate analysis in speech recognition. In Proceedings of IEEE international conference on acoustics, speech, and signal processing."}],"container-title":["Wireless Personal Communications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11277-017-4544-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-017-4544-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-017-4544-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,24]],"date-time":"2024-06-24T12:27:54Z","timestamp":1719232074000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11277-017-4544-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5,30]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,11]]}},"alternative-id":["4544"],"URL":"https:\/\/doi.org\/10.1007\/s11277-017-4544-1","relation":{},"ISSN":["0929-6212","1572-834X"],"issn-type":[{"type":"print","value":"0929-6212"},{"type":"electronic","value":"1572-834X"}],"subject":[],"published":{"date-parts":[[2017,5,30]]}}}