{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T11:42:18Z","timestamp":1725536538089},"publisher-location":"Berlin, Heidelberg","reference-count":19,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642042072"},{"type":"electronic","value":"9783642042089"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009]]},"DOI":"10.1007\/978-3-642-04208-9_46","type":"book-chapter","created":{"date-parts":[[2009,8,25]],"date-time":"2009-08-25T04:27:42Z","timestamp":1251174462000},"page":"331-338","source":"Crossref","is-referenced-by-count":7,"title":["Discriminative Training of Gender-Dependent Acoustic Models"],"prefix":"10.1007","author":[{"given":"Jan","family":"Van\u011bk","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josef V.","family":"Psutka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Zelinka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ale\u0161","family":"Pra\u017e\u00e1k","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josef","family":"Psutka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"46_CR1","unstructured":"Stolcke, A., Bratt, H., Butzberger, J., Franco, H., Gadde, V.R., Rao, P.M., Rickey, C., Shriberg, E., Sonmez, K., Weng, F., Zheng, J.: The SRI Hub-5 Conversational Speech Transcription System. In: Proc. NIST Speech Transcription Workshop, College Park, MD (March 2000)"},{"key":"46_CR2","unstructured":"Zelinka, J.: Audio-visual speech recognition. PhD. thesis, University of West Bohemia, Department of Cybernetics (2009) (in Czech)"},{"key":"46_CR3","unstructured":"Povey, D.: Discriminative Training for Large Vocabulary Speech Recognition. Ph.D. thesis, Cambridge University, Department of Engineering (2003)"},{"key":"46_CR4","doi-asserted-by":"crossref","unstructured":"Yu, D., Deng, L., He, X., Acero, A.: Use of incrementally regulated discriminative margins in MCE training for speech recognition. In: Proc. Interspeech 2006 (2006)","DOI":"10.21437\/Interspeech.2006-606"},{"key":"46_CR5","unstructured":"McDermott, E., Hazen, T., Roux, J.L., Nakamura, A., Katagiri, S.: Discriminative training for large vocabulary speech recognition using minimum classification error. IEEE Trans. Speech and Audio Proc.\u00a014(2) (2006)"},{"key":"46_CR6","doi-asserted-by":"crossref","unstructured":"Reichl, W., Ruske, G.: Discriminative Training for Continuous Speech Recognition. In: Proc. 1995 Europ. Conf. on Speech Communication and Technology, Madrid, September 1995, vol.\u00a01, pp. 537\u2013540 (1995)","DOI":"10.21437\/Eurospeech.1995-29"},{"key":"46_CR7","doi-asserted-by":"crossref","unstructured":"Bahl, L.R., Brown, P.F., de Souza, P.V., Mercer, L.R.: Maximum Mutual Information Estimation of Hidden Markov Model Parameters for Speech Recognition. In: ICASSP (1986)","DOI":"10.1109\/ICASSP.1986.1169179"},{"key":"46_CR8","unstructured":"Kapadia, S.: Discriminative Training of Hidden Markov Models. Ph.D. thesis, Cambridge University, Department of Engineering (1998)"},{"key":"46_CR9","doi-asserted-by":"crossref","unstructured":"Povey, D., Woodland, P.C.: Improved discriminative training techniques for large vocabulary continuous speech recognition. In: IEEE international Conference on Acoustics Speech and Signal Processing, Salt Lake City, Utah, May 7-11 (2001)","DOI":"10.1109\/ICASSP.2001.940763"},{"key":"46_CR10","doi-asserted-by":"crossref","unstructured":"Povey, D., Woodland, P.C.: Frame discrimination training for HMMs for large vocabulary speechrecognition. In: Proceedings of the ICASSP, Phoenix, USA (1999)","DOI":"10.1109\/ICASSP.1999.758130"},{"key":"46_CR11","doi-asserted-by":"crossref","unstructured":"Gauvain, L., Lee, C.H.: Maximum A-Posteriori Estimation for Multivariate Gaussian Mixture Observations of Markov Chains. In: IEEE Transactions SAP (1994)","DOI":"10.1109\/89.279278"},{"key":"46_CR12","doi-asserted-by":"crossref","unstructured":"Povey, D., Gales, M.J.F., Kim, D.Y., Woodland, P.C.: MMI-MAP and MPE-MAP for acoustic model adaptation. In: EUROSPEECH, pp. 1981\u20131984 (2003)","DOI":"10.21437\/Eurospeech.2003-572"},{"key":"46_CR13","doi-asserted-by":"crossref","unstructured":"Povey, D., Woodland, P.: Minimum phone error and I-smoothing for improved discriminative training. In: Proceedings of the ICASSP, Orlando, USA (2002)","DOI":"10.1109\/ICASSP.2002.5743665"},{"key":"46_CR14","doi-asserted-by":"crossref","unstructured":"Radov\u00e1, V., Psutka, J.: UWB-S01 Corpus: A Czech Read-Speech Corpus. In: Proceedings of the 6th International Conference on Spoken Language Processing ICSLP2000, Beijing, China (2000)","DOI":"10.21437\/ICSLP.2000-916"},{"key":"46_CR15","doi-asserted-by":"crossref","unstructured":"Psutka, J., M\u00fcller, L., Psutka, J.V.: Comparison of MFCC and PLP Parameterization in the Speaker Independent Continuous Speech Recognition Task. In: 7th European Conference on Speech Communication and Technology (EUROSPEECH 2001), Aalborg, Denmark (2001)","DOI":"10.21437\/Eurospeech.2001-428"},{"key":"46_CR16","doi-asserted-by":"crossref","unstructured":"Hermansky, H.: Perceptual linear predictive (PLP) analysis of speech. J. Acoustic. Soc. Am. 87 (1990)","DOI":"10.1121\/1.399423"},{"key":"46_CR17","volume-title":"SPECOM 2007 Proceedings","author":"J. Psutka","year":"2007","unstructured":"Psutka, J.: Robust PLP-Based Parameterization for ASR Systems. In: SPECOM 2007 Proceedings. Moscow State Linguistic University, Moscow (2007)"},{"key":"46_CR18","unstructured":"Young, s., et al.: The HTK Book (for HTK Version 3.4), Cambridge (2006)"},{"key":"46_CR19","doi-asserted-by":"crossref","unstructured":"Stolcke, A.: SRILM - An Extensible Language Modeling Toolkit. In: International Conference on Spoken Language Processing (ICSLP 2002), Denver, USA (2002)","DOI":"10.21437\/ICSLP.2002-303"}],"container-title":["Lecture Notes in Computer Science","Text, Speech and Dialogue"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-04208-9_46","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,26]],"date-time":"2023-05-26T12:57:41Z","timestamp":1685105861000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-04208-9_46"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642042072","9783642042089"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-04208-9_46","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2009]]}}}