{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T22:22:51Z","timestamp":1785363771784,"version":"3.55.0"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[1998,7,1]],"date-time":"1998-07-01T00:00:00Z","timestamp":899251200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[1998,7,1]],"date-time":"1998-07-01T00:00:00Z","timestamp":899251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Learning"],"published-print":{"date-parts":[[1998,7]]},"DOI":"10.1023\/a:1007469218079","type":"journal-article","created":{"date-parts":[[2002,12,22]],"date-time":"2002-12-22T04:48:21Z","timestamp":1040532501000},"page":"41-62","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":581,"title":["The Hierarchical Hidden Markov Model: Analysis and Applications"],"prefix":"10.1007","volume":"32","author":[{"given":"Shai","family":"Fine","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoram","family":"Singer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naftali","family":"Tishby","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"160199_CR1","first-page":"205","volume":"9","author":"N. Abe","year":"1992","unstructured":"Abe, N. & Warmuth, M. (1992). On the computational complexity of approximating distributions by probabilistic automata. Machine Learning, 9:205-260.","journal-title":"Machine Learning"},{"issue":"3","key":"160199_CR2","doi-asserted-by":"crossref","first-page":"1059","DOI":"10.1073\/pnas.91.3.1059","volume":"91","author":"P. Baldi","year":"1994","unstructured":"Baldi, P., Chauvin, Y., Hunkapiller, T. & McClure, M. (1994). Hidden Markov models of biological primary sequence information. Proc. Nat. Acd. Sci. (USA), 91(3):1059-1063.","journal-title":"Proc. Nat. Acd. Sci. (USA)"},{"key":"160199_CR3","doi-asserted-by":"crossref","unstructured":"Baum, L.E. & Petrie, T. (1966). Statistical inference for probabilistic functions of finite state Markov chains. Annals of Mathematical Statistics, Vol. 37.","DOI":"10.1214\/aoms\/1177699147"},{"key":"160199_CR4","first-page":"427","volume-title":"Advances in Neural Information Processing Systems","author":"Y. Bengio","year":"1995","unstructured":"Bengio, Y. & Frasconi, P. (1995). An input-output HMM architecture. In G. Tesauro, D.S. Touretzky, and T.K. Leen, editors, Advances in Neural Information Processing Systems 7, pages 427-434. MIT Press, Cambridge, MA."},{"key":"160199_CR5","unstructured":"Cover, T. & Thomas, J. (1991). Elements of Information Theory. Wiley."},{"key":"160199_CR6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"A.P. Dempster","year":"1977","unstructured":"Dempster, A.P., Laird, N.M. & Rubin, D.B. (1977). Maximum-likelihood from incomplete data via the EM algorithm. Journal of Royal Statistical Society, Series B, 39:1-38.","journal-title":"Journal of Royal Statistical Society, Series B"},{"issue":"3","key":"160199_CR7","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1088\/0954-898X_8_3_005","volume":"8","author":"I. Gat","year":"1997","unstructured":"Gat, I., Tishby, N. & Abeles, M. (1997). Hidden Markov modeling of simultaneously recorded cells in the associative cortex of behaving monkeys. Network: Computation in neural systems, 8:3, pages 297-322.","journal-title":"Network: Computation in neural systems"},{"key":"160199_CR8","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1023\/A:1007425814087","volume":"29","author":"Z. Ghahramani","year":"1997","unstructured":"Ghahramani Z. & Jordan, M.I. (1997). Factorial hidden Markov models. Machine Learning, 29: 245-273.","journal-title":"Machine Learning"},{"key":"160199_CR9","doi-asserted-by":"crossref","unstructured":"Gillman, D. & Sipser, M. (1994). Inference and minimization of hidden Markov chains. Proceedings of the Seventh Annual Workshop on Computational Learning Theory, pages 147-158.","DOI":"10.1145\/180139.181091"},{"key":"160199_CR10","unstructured":"Jelinek, F. (1985). Robust part-of-speech tagging using a hidden Markov model. IBM T.J. Watson Research Technical Report."},{"key":"160199_CR11","unstructured":"Jelinek, F. (1983). Markov source modeling of text generation. Technical report, IBM T.J. Watson Research Center Technical Report."},{"key":"160199_CR12","unstructured":"Jelinek, F. (1985). Self-organized language modeling for speech recognition. IBM T.J. Watson Research Center Technical Report."},{"key":"160199_CR13","doi-asserted-by":"crossref","first-page":"4768","DOI":"10.1093\/nar\/22.22.4768","volume":"22","author":"A. Krogh","year":"1994","unstructured":"Krogh, A., Mian, S.I. & Haussler, D. (1994). A hidden Markov model that finds genes in E.coli DNA. NAR, 22\u201d4768-4778.","journal-title":"NAR"},{"key":"160199_CR14","doi-asserted-by":"crossref","unstructured":"Lari, K. & Young, S.J. (1990). The estimation of stochastic context free grammars using the Inside-Outside algorithm. Computers Speech and Language, 4.","DOI":"10.1016\/0885-2308(90)90022-X"},{"key":"160199_CR15","doi-asserted-by":"crossref","unstructured":"Nag, R., Wong, K.H. & Fallside, F. (1985). Script recognition using hidden Markov models. Proceedings of International Conference on Acoustics Speech and Signal Processing, pages 2071-2074.","DOI":"10.1109\/ICASSP.1986.1168951"},{"key":"160199_CR16","doi-asserted-by":"crossref","unstructured":"Rabiner, L.R. & Juang, B.H. (1986). An introduction to hidden Markov models. IEEE ASSP Magazine, No. 3.","DOI":"10.1109\/MASSP.1986.1165342"},{"key":"160199_CR17","doi-asserted-by":"crossref","unstructured":"Rabiner, L.R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE.","DOI":"10.1016\/B978-0-08-051584-7.50027-9"},{"issue":"4","key":"160199_CR18","doi-asserted-by":"crossref","first-page":"526","DOI":"10.1109\/TIT.1986.1057210","volume":"32","author":"J. Rissanen","year":"1986","unstructured":"Rissanen, J. (1986). Complexity of strings in the class of Markov sources. IEEE Transactions on Information Theory, 32(4):526-532.","journal-title":"IEEE Transactions on Information Theory"},{"key":"160199_CR19","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1023\/A:1026490906255","volume":"25","author":"D. Ron","year":"1996","unstructured":"Ron, D., Singer, Y. & Tishby, N. (1996). The power of amnesia: learning probabilistic automata with variable memory length. Machine Learning, 25:117-149.","journal-title":"Machine Learning"},{"issue":"3","key":"160199_CR20","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1007\/BF00202762","volume":"71","author":"Y. Singer","year":"1994","unstructured":"Singer, Y. & Tishby, N.. (1994). Dynamical encoding of cursive handwriting. Biological Cybernetics, 71(3):227-237.","journal-title":"Biological Cybernetics"},{"key":"160199_CR21","first-page":"641","volume-title":"Advances in Neural Information Processing Systems","author":"Y. Singer","year":"1997","unstructured":"Singer, Y. & Warmuth, M.K. (1997). Training algorithms for hidden Markov models using entropy based distance functions. In M.C. Mozer, M.I. Jordan, and T. Petsche, editors, Advances in Neural Information Processing Systems 9, pages 641-647. MIT Press, Cambridge, MA."},{"key":"160199_CR22","unstructured":"Stolcke A. & Omohundro, S.M. (1994). Best-first model merging for hidden Markov model induction. Technical Report ICSI TR-94-003."},{"key":"160199_CR23","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1109\/TIT.1967.1054010","volume":"13","author":"A.J. Viterbi","year":"1967","unstructured":"Viterbi, A.J. (1967). Error bounds for convulutional codes and an asymptotically optimal decoding algorithm. IEEE Transactions on Information Theory, 13:260-269.","journal-title":"IEEE Transactions on Information Theory"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1007469218079.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1007469218079\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1007469218079.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T11:42:27Z","timestamp":1752147747000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1007469218079"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1998,7]]},"references-count":23,"journal-issue":{"issue":"1","published-print":{"date-parts":[[1998,7]]}},"alternative-id":["160199"],"URL":"https:\/\/doi.org\/10.1023\/a:1007469218079","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[1998,7]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}