{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T13:10:05Z","timestamp":1746364205409,"version":"3.40.4"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319113968"},{"type":"electronic","value":"9783319113975"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-11397-5_8","type":"book-chapter","created":{"date-parts":[[2014,9,2]],"date-time":"2014-09-02T06:41:19Z","timestamp":1409640079000},"page":"108-119","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Structured GMM Based on Unsupervised Clustering for Recognizing Adult and Child Speech"],"prefix":"10.1007","author":[{"given":"Arseniy","family":"Gorin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Denis","family":"Jouvet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,9,3]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Beaufays, F., Vanhoucke, V., Strope, B.: Unsupervised discovery and training of maximally dissimilar cluster models. In: Proceedings of the INTERSPEECH, Makuhari, Japan, pp. 66\u201369 (2010), http:\/\/www.isca-speech.org\/archive\/interspeech_2004\/i04_0377.html","DOI":"10.21437\/Interspeech.2010-13"},{"issue":"10","key":"8_CR2","doi-asserted-by":"publisher","first-page":"763","DOI":"10.1016\/j.specom.2007.02.006","volume":"49","author":"M Benzeghiba","year":"2007","unstructured":"Benzeghiba, M., De Mori, R., Deroo, O., Dupont, S., Erbes, T., Jouvet, D., Fissore, L., Laface, P., Mertins, A., Ris, C., Tyagi, V., Wellekens, C.: Automatic speech recognition and speech variability: a review. Speech Commun. 49(10), 763\u2013786 (2007)","journal-title":"Speech Commun."},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Burnett, D.C., Fanty, M.: Rapid unsupervised adaptation to children\u2019s speech on a connected-digit task. In: Proceedings of the ICSLP, vol. 2, pp. 1145\u20131148. IEEE (1996)","DOI":"10.21437\/ICSLP.1996-255"},{"key":"8_CR4","unstructured":"CMU: Sphinx toolkit (2014), http:\/\/cmusphinx.sourceforge.net"},{"issue":"2","key":"8_CR5","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1006\/csla.1998.0043","volume":"12","author":"MJ Gales","year":"1998","unstructured":"Gales, M.J.: Maximum likelihood linear transformations for HMM-based speech recognition. Comput. Speech Lang. 12(2), 75\u201398 (1998)","journal-title":"Comput. Speech Lang."},{"issue":"2","key":"8_CR6","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1109\/89.279278","volume":"2","author":"JL Gauvain","year":"1994","unstructured":"Gauvain, J.L., Lee, C.H.: Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains. IEEE Trans. Speech Audio Process. 2(2), 291\u2013298 (1994)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Gorin, A., Jouvet, D.: Class-based speech recognition using a maximum dissimilarity criterion and a tolerance classification margin. In: 2012 IEEE Proceedings of the Spoken Language Technology Workshop (SLT), pp. 91\u201396. IEEE (2012)","DOI":"10.1109\/SLT.2012.6424203"},{"key":"8_CR8","unstructured":"Gorin, A., Jouvet, D.: Efficient constrained parametrization of GMM with class-based mixture weights for automatic speech recognition. In: Proceedings of the LTC-6th Language & Technologies Conference, pp. 550\u2013554 (2013)"},{"key":"8_CR9","unstructured":"Jouvet, D., Gorin, A., Vinuesa, N.: Exploitation d\u2019une marge de tol\u00e9rance de classification pour am\u00e9liorer l\u2019apprentissage de mod\u00e8les acoustiques de classes en reconnaissance de la parole. In: JEP-TALN-RECITAL, pp. 763\u2013770 (2012)"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Kuhn, R., Nguyen, P., Junqua, J.C., Goldwasser, L., Niedzielski, N., Fincke, S., Field, K., Contolini, M.: Eigenvoices for speaker adaptation. In: Proceedings of the ICSLP, vol. 98, pp. 1774\u20131777 (1998)","DOI":"10.21437\/ICSLP.1998-740"},{"key":"8_CR11","unstructured":"Leonard, R.G., Doddington, G.: Tidigits speech corpus. Texas Instruments, Inc. (1993)"},{"issue":"5","key":"8_CR12","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1109\/JPROC.2013.2251592","volume":"101","author":"D O\u2019Shaughnessy","year":"2013","unstructured":"O\u2019Shaughnessy, D.: Acoustic analysis for automatic speech recognition. Proc. IEEE 101(5), 1038\u20131053 (2013)","journal-title":"Proc. IEEE"},{"issue":"1","key":"8_CR13","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.csl.2008.02.003","volume":"23","author":"S Panchapagesan","year":"2009","unstructured":"Panchapagesan, S., Alwan, A.: Frequency warping for vtln and speaker adaptation by linear transformation of standard mfcc. Computer Speech Lang. 23(1), 42\u201364 (2009)","journal-title":"Computer Speech Lang."},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Stern, R.M., Morgan, N.: Hearing is believing: Biologically inspired methods for robust automatic speech recognition. IEEE Signal Process. Mag. 29(6), 34\u201343 (2012), http:\/\/ieeexplore.ieee.org\/xpls\/abs_all.jsp?arnumber=6296528","DOI":"10.1109\/MSP.2012.2207989"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Wellekens, C.J.: Explicit time correlation in hidden Markov models for speech recognition. In: Proceedings of the ICASSP, pp. 384\u2013386 (1987)","DOI":"10.1109\/ICASSP.1987.1169614"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Wenxuan, T., Gravier, G., Bimbot, F., Soufflet, F.: Rapid speaker adaptation by reference model interpolation. In: Proceedings of the INTERSPEECH, pp. 258\u2013261 (2007)","DOI":"10.21437\/Interspeech.2007-116"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Zhan, P., Waibel, A.: Vocal tract length normalization for large vocabulary continuous speech recognition. Technical report. DTIC Document (1997)","DOI":"10.21236\/ADA333514"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Juang, B.H.: Stranded Gaussian mixture hidden Markov models for robust speech recognition. In: Proceedings of the ICASSP, pp. 4301\u20134304 (2012)","DOI":"10.1109\/ICASSP.2012.6288870"}],"container-title":["Lecture Notes in Computer Science","Statistical Language and Speech Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-11397-5_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T12:31:50Z","timestamp":1746361910000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-11397-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319113968","9783319113975"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-11397-5_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]},"assertion":[{"value":"3 September 2014","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}