{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,5,30]],"date-time":"2022-05-30T01:51:23Z","timestamp":1653875483666},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2011,10,6]],"date-time":"2011-10-06T00:00:00Z","timestamp":1317859200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Telecommun Syst"],"published-print":{"date-parts":[[2013,3]]},"DOI":"10.1007\/s11235-011-9660-8","type":"journal-article","created":{"date-parts":[[2011,10,5]],"date-time":"2011-10-05T19:51:53Z","timestamp":1317844313000},"page":"1683-1696","source":"Crossref","is-referenced-by-count":2,"title":["Building accurate and robust HMM models for practical ASR systems"],"prefix":"10.1007","volume":"52","author":[{"given":"Juraj","family":"Ka\u010dur","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gregor","family":"Rozinaj","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2011,10,6]]},"reference":[{"key":"9660_CR1","doi-asserted-by":"crossref","first-page":"1681","DOI":"10.21437\/Interspeech.2005-548","volume-title":"Proceedings of interspeech 2005","author":"J. Nouza","year":"2005","unstructured":"Nouza, J., Zdansky, J., David, P., Cerva, P., Kolorenc, J., & Nejedlova, D. (2005). Fully automated system for Czech spoken broadcast transcription with very large (300K+) lexicon. In Proceedings of interspeech 2005, Lisbon, Portugal, September, 2005 (pp. 1681\u20131684). ISSN 1018-4074."},{"key":"9660_CR2","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1090\/S0002-9904-1967-11751-8","volume":"73","author":"L. Baum","year":"1967","unstructured":"Baum, L., & Eagon, J. (1967). An inequality with applications to statistical estimation for probabilities functions of a Markov process and to models for ecology. Bulletin of the AMS, 73, 360\u2013363.","journal-title":"Bulletin of the AMS"},{"key":"9660_CR3","unstructured":"Huang, X., Ariki, Y., & Jack, M. (1990). Hidden Markov models for speech recognition. Edinburg University Press."},{"key":"9660_CR4","doi-asserted-by":"crossref","unstructured":"Jiang, H., & Li, X. (2007). A general approximation-optimization approach to large margin estimation of HMMs. In Robust speech recognition and understanding. I-Tech education and publishing, Croatia, ISBN 978-3-902613-08-0.","DOI":"10.5772\/4746"},{"key":"9660_CR5","unstructured":"Bonafonte, A., Vidal, J., & Nogueiras, A. (1996). Duration modeling with expanded HMM applied to speech recognition. In Proceedings of ICSLP 96, Philadelphia, USA (Vol.\u00a02, pp.\u00a01097\u20131100). ISBN: 0-7803-3555-4."},{"key":"9660_CR6","doi-asserted-by":"crossref","unstructured":"Casar, M., & Fonllosa, J. (2007). Double layer architectures for automatic speech recognition using HMM. In Robust speech recognition and understanding. I-Tech education and publishing, Croatia. ISBN 978-3-902613-08-0.","DOI":"10.5772\/4747"},{"key":"9660_CR7","unstructured":"Hermasky, H., & Morgan, N. (1994). RASTA processing of speech. IEEE Transactions on Speech and Audio Processing, 2(4)."},{"key":"9660_CR8","doi-asserted-by":"crossref","unstructured":"Nadeu, C., & Macho, D. (2001). Time and Frequency Filtering of Filter-Bank energies for robust HMM speech recognition. Speech Communication, 34.","DOI":"10.1016\/S0167-6393(00)00048-0"},{"key":"9660_CR9","unstructured":"Cheng, O., Abdulla, W., & Salcic, Z. (2005). Performance evaluation of front-end processing for speech recognition systems. School of Engineering Report No. 621, Electrical and Computer Engineering Department, School of Engineering, The University of Auckland."},{"key":"9660_CR10","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.specom.2008.06.002","volume":"51","author":"S. Haque","year":"2009","unstructured":"Haque, S., Togneri, R., & Zaknich, A. (2009). Perceptual features for automatic speech recognition in noisy environments. Speech Communication, 51, 58\u201375.","journal-title":"Speech Communication"},{"key":"9660_CR11","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1214\/aos\/1176346060","volume":"11","author":"C. F. J. Wu","year":"1983","unstructured":"Wu, C. F. J. (1983). On the convergence properties of the EM algorithm. The Annals of Statistics, 11, 95\u2013103.","journal-title":"The Annals of Statistics"},{"key":"9660_CR12","first-page":"449","volume-title":"Proceedings of the 11-th international conference speech and computer (SPECOM\u20192006)","author":"S. Darjaa","year":"2006","unstructured":"Darjaa, S., Rusko, M., & Trnka, M. (2006). MobilDat-SK\u2013a mobile telephone extension to the SpeechDat-E SK telephone speech database in Slovak. In Proceedings of the 11-th international conference speech and computer (SPECOM\u20192006), St. Petersburg, Russia (pp. 449\u2013454)."},{"key":"9660_CR13","unstructured":"Zgank, A., Kacic, Z., Diehel, F., Vicsi, K., Szaszak, G., Juhar, J., & Lihan, S. (2004). The Cost 278 MASPER initiative\u2014crosslingual speech recognition with large telephone databases. In Proceedings of language resources and evaluation (LREC), Lisbon (pp. 2107\u20132110)."},{"key":"9660_CR14","unstructured":"Lindberg, B., Johansen, F., Warakagoda, N., Lehtinen, G., Kacic, Z., Zgang, A., Elenius, K., & Salvi, G. (2000). A noise robust multilingual reference recognizer based on SpeechDat(II). In Proceedings of ICSLP 2000, Beijing, China, October 2000."},{"key":"9660_CR15","isbn-type":"print","volume-title":"Fundamentals of speech recognition","author":"L. Rabiner","year":"1993","unstructured":"Rabiner, L., & Juan, B. (1993). Fundamentals of speech recognition. New Jersey: Prentice Hall. ISBN 0-13-015157-2","ISBN":"http:\/\/id.crossref.org\/isbn\/0130151572"},{"key":"9660_CR16","doi-asserted-by":"crossref","first-page":"2997","DOI":"10.21437\/Interspeech.2005-138","volume-title":"Proceedings of INTERSPEECH","author":"F. H\u00f6nig","year":"2005","unstructured":"H\u00f6nig, F., Stemmer, G., Hacker, Ch., & Brugnara, F. (2005). Revising perceptual linear prediction (PLP). In Proceedings of INTERSPEECH, Lisbon, Portugal, Sept. 2005 (pp. 2997\u20133000)."},{"key":"9660_CR17","doi-asserted-by":"crossref","unstructured":"Lee, K., Hon, H., & Reddy, R. (1990). An overview of the SPHINX speech recognition system. IEEE Transactions on Acoustics Speech and Signal Processing, 38(1).","DOI":"10.1109\/29.45616"},{"key":"9660_CR18","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP.1985.1168384","volume-title":"Perceptually based linear predictive analysis of speech","author":"H. Hermansky","year":"1985","unstructured":"Hermansky, H., Hanson, B. A., & Wakita, H. (1985). Perceptually based linear predictive analysis of speech. New York: IEEE."},{"key":"9660_CR19","volume-title":"ISCCSP","author":"A. Rabaoui","year":"2008","unstructured":"Rabaoui, A., Kadri, H., Lachiri, Z., & Ellouze, N. (2008). Using robust features with multi-class SVMs to classify noisy sounds. In ISCCSP, Malta."},{"key":"9660_CR20","doi-asserted-by":"crossref","unstructured":"Cheveigne, A., & Kawahara, H. (2002). YIN, a fundamental frequency estimator for speech and music. Journal of the Acoustical Society of America, 111(4).","DOI":"10.1121\/1.1458024"},{"key":"9660_CR21","volume-title":"IWSSIP09","author":"J. Kacur","year":"2009","unstructured":"Kacur, J., & Rozinaj, G. (2009). Adding voicing features into speech recognition based on HMM in Slovak. In IWSSIP09, Greece."},{"key":"9660_CR22","first-page":"34","volume-title":"ECAI 2006 workshop on language-enabled educational technology and development and evaluation of robust spoken dialogue systems","author":"J. Juhar","year":"2006","unstructured":"Juhar, J., Ondas, S., Cizmar, A., Rusko, M., Rozinaj, G., & Jarina, R. (2006). Galaxy\/VoiceXML based spoken Slovak dialogue system to access the Internet. In ECAI 2006 workshop on language-enabled educational technology and development and evaluation of robust spoken dialogue systems, Riva del Garda, Italy, August 29, 2006 (pp. 34\u201337)."},{"key":"9660_CR23","volume-title":"2nd international conference on language resources and evaluation (LREC-2000)","author":"F. T. Johansen","year":"2000","unstructured":"Johansen, F. T., Warakagoda, N., Lindberg, B., et al. (2000). The cost 249 SpeechDat multilingual reference recognizer. In 2nd international conference on language resources and evaluation (LREC-2000), Athens, May 2000."},{"key":"9660_CR24","volume-title":"Proc. Europ. conf. speech proc. and techn. (EUROSPEECH)","author":"H. H\u00f6ge","year":"1999","unstructured":"H\u00f6ge, H., Draxler, C., Van\u00a0den Heuvel, H., Johansen, F. T., Sanders, E., & Tropf, H. S. (1999). SpeechDat multilingual speech databases for teleservices: across the finish line. In Proc. Europ. conf. speech proc. and techn. (EUROSPEECH)."},{"key":"9660_CR25","unstructured":"Young, S., Evermann, G., & Hain, T. (2002). The HTK book V.3.2.1. Cambridge University Engineering Department."},{"key":"9660_CR26","volume-title":"IWSSIP07","author":"J. Kacur","year":"2007","unstructured":"Kacur, J., & Ceresna, M. (2007). A modified MASPER training procedure for ASR systems and its performance on Slovak MOBILDAT database. In IWSSIP07, Slovenia."}],"container-title":["Telecommunication Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11235-011-9660-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11235-011-9660-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11235-011-9660-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,9]],"date-time":"2021-12-09T03:52:27Z","timestamp":1639021947000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11235-011-9660-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,10,6]]},"references-count":26,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2013,3]]}},"alternative-id":["9660"],"URL":"https:\/\/doi.org\/10.1007\/s11235-011-9660-8","relation":{},"ISSN":["1018-4864","1572-9451"],"issn-type":[{"value":"1018-4864","type":"print"},{"value":"1572-9451","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,10,6]]}}}