{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:30:22Z","timestamp":1781109022341,"version":"3.54.1"},"reference-count":34,"publisher":"IGI Global Scientific Publishing","issue":"3","license":[{"start":{"date-parts":[[2014,7,1]],"date-time":"2014-07-01T00:00:00Z","timestamp":1404172800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/3.0\/deed.en_US"},{"start":{"date-parts":[[2014,7,1]],"date-time":"2014-07-01T00:00:00Z","timestamp":1404172800000},"content-version":"am","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/3.0\/deed.en_US"},{"start":{"date-parts":[[2014,7,1]],"date-time":"2014-07-01T00:00:00Z","timestamp":1404172800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/3.0\/deed.en_US"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,7,1]]},"abstract":"<p>Tied-mixture HMMs have been proposed as the acoustic model for large-vocabulary continuous speech recognition and have yielded promising results. They share base-distribution and provide more flexibility in choosing the degree of tying than state-clustered HMMs. However, it is unclear which acoustic models to superior to the other under the same training data. Moreover, LBG algorithm and EM algorithm, which are the usual training methods for HMMs, have not been compared. Therefore in this paper, the recognition performance of the respective HMMs and the respective training methods are compared under the same condition. It was found that the number of parameters and the word error rate for both HMMs are equivalent when the number of codebooks is sufficiently large. It was also found that training method using the LBG algorithm achieves a 90% reduction in training time compared to training method using the EM algorithm, without degradation of recognition accuracy.<\/p>","DOI":"10.4018\/jitr.2014070102","type":"journal-article","created":{"date-parts":[[2014,10,7]],"date-time":"2014-10-07T11:37:19Z","timestamp":1412681839000},"page":"1-17","source":"Crossref","is-referenced-by-count":0,"title":["Comparison of Tied-Mixture and State-Clustered HMMs with Respect to Recognition Performance and Training Method"],"prefix":"10.4018","volume":"7","author":[{"given":"Hiroyuki","family":"Segi","sequence":"first","affiliation":[{"name":"NHK (Japan Broadcasting Corporation) Science & Technology Research Laboratories, Fukushima, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuo","family":"Onoe","sequence":"additional","affiliation":[{"name":"NHK (Japan Broadcasting Corporation), Science & Technology Research Laboratories, Fukushima, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shoei","family":"Sato","sequence":"additional","affiliation":[{"name":"NHK (Japan Broadcasting Corporation) Science & Technology Research Laboratories, Fukushima, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akio","family":"Kobayashi","sequence":"additional","affiliation":[{"name":"NHK (Japan Broadcasting Corporation) Science & Technology Research Laboratories, Fukushima, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akio","family":"Ando","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, University of Toyoma, Toyoma, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"2432","reference":[{"issue":"1","key":"jitr.2014070102-0","first-page":"15","article-title":"Simultaneous subtitling system for broadcast news programs with a speech recognizer.","volume":"E86-D","author":"A.Ando","year":"2003","journal-title":"IEICE Transactions on Information and Systems"},{"key":"jitr.2014070102-1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1983.4767370"},{"key":"jitr.2014070102-2","doi-asserted-by":"crossref","first-page":"2707","DOI":"10.21437\/Eurospeech.1997-683","article-title":"Statistical language modeling using the CMU\u2013Cambridge toolkit.","author":"P.Clarkson","year":"1997","journal-title":"Proceedings of the Eurospeech"},{"key":"jitr.2014070102-3","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2012.07.006"},{"issue":"1","key":"jitr.2014070102-4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the EM algorithm.","volume":"39","author":"A.Dempster","year":"1977","journal-title":"Journal of the Royal Statistical Society. Series A (General)"},{"key":"jitr.2014070102-5","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075886"},{"key":"jitr.2014070102-6","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E95.D.2084"},{"key":"jitr.2014070102-7","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1993.1019"},{"key":"jitr.2014070102-8","doi-asserted-by":"publisher","DOI":"10.1109\/89.544526"},{"key":"jitr.2014070102-9","doi-asserted-by":"publisher","DOI":"10.1250\/ast.21.29"},{"key":"jitr.2014070102-10","first-page":"89","article-title":"Design of a Japanese sentence list for a speech database.","author":"K.Iso","year":"1988","journal-title":"Proceedings of the Spring Meeting of the Acoustical Society of Japan"},{"key":"jitr.2014070102-11","first-page":"3261","article-title":"The design of the newspaper-based Japanese large vocabulary continuous speech recognition corpus.","author":"K.Itou","year":"1998","journal-title":"Proceedings of the International Conference on Spoken Language Processing (ICSLP)"},{"key":"jitr.2014070102-12","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1987.1165125"},{"key":"jitr.2014070102-13","doi-asserted-by":"crossref","first-page":"2224","DOI":"10.1609\/aaai.v26i2.18962","article-title":"Transcription system using automatic speech recognition for the Japanese Parliament (Diet).","author":"T.Kawahara","year":"2012","journal-title":"Proceedings of the Twenty-Fourth Innovative Applications of Artificial Intelligence Conference"},{"key":"jitr.2014070102-14","unstructured":"Kobayashi, A., Fujita, Y., Oku, T., Sato, S., Homma, S., Arai, T., & Imai, T. (2013). Live closed-captioning system using hybrid automatic speech recognition for broadcast news. In Proceedings of the National Association of Broadcasters Broadcast Engineering Conference (NAB BEC) (pp. 277-283)."},{"key":"jitr.2014070102-15","first-page":"2435","article-title":"Time dependent language model for broadcast news transcription and its post-correction.","author":"A.Kobayashi","year":"1998","journal-title":"Proceedings of the International Conference on Spoken Language Processing (ICSLP)"},{"key":"jitr.2014070102-16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861808"},{"key":"jitr.2014070102-17","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1980.1094577"},{"key":"jitr.2014070102-18","doi-asserted-by":"publisher","DOI":"10.1121\/1.4768800"},{"key":"jitr.2014070102-19","first-page":"947","article-title":"Spontaneous speech corpus of Japanese.","author":"K.Maekawa","year":"2000","journal-title":"Proceedings of the Second International Conference of Language Resources and Evaluation (LREC)"},{"key":"jitr.2014070102-20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225985"},{"key":"jitr.2014070102-21","first-page":"77","article-title":"The 1994 BBN\/BYBLOS speech recognition system.","author":"L.Nguyen","year":"1995","journal-title":"Proceedings of the ARPA Spoken Language Systems Technology Workshop"},{"key":"jitr.2014070102-22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289024"},{"issue":"3","key":"jitr.2014070102-23","first-page":"483","article-title":"Filter bank subtraction for robust speech recognition.","volume":"E86-D","author":"K.Onoe","year":"2003","journal-title":"IEICE Transactions on Information and Systems"},{"key":"jitr.2014070102-24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.1005687"},{"key":"jitr.2014070102-25","first-page":"2219","article-title":"A new look at HMM parameter tying for large vocabulary speech recognition.","author":"A.Sankar","year":"1998","journal-title":"Proceedings of the International Conference on Spoken Language Processing (ICSLP)"},{"key":"jitr.2014070102-26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1991.150436"},{"key":"jitr.2014070102-27","first-page":"123","article-title":"An examination of decision tree and the number of models on state tying triphone HMM.","author":"H.Segi","year":"1999","journal-title":"Proceedings of the Autumn Meeting of the Acoustical Society of Japan"},{"key":"jitr.2014070102-28","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2010.5439141"},{"key":"jitr.2014070102-29","article-title":"A signal-separation-based array postfilter for distant speech recognition.","author":"R.Singh","year":"2012","journal-title":"Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH)"},{"key":"jitr.2014070102-30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288891"},{"key":"jitr.2014070102-31","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1054010"},{"key":"jitr.2014070102-32","author":"S.Young","year":"2009","journal-title":"The HTK book"},{"key":"jitr.2014070102-33","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075885"}],"container-title":["Journal of Information Technology Research"],"original-title":[],"language":"ng","link":[{"URL":"https:\/\/www.igi-global.com\/viewtitle.aspx?TitleId=116635","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T11:04:58Z","timestamp":1717412698000},"score":1,"resource":{"primary":{"URL":"https:\/\/services.igi-global.com\/resolvedoi\/resolve.aspx?doi=10.4018\/jitr.2014070102"}},"subtitle":[""],"short-title":[],"issued":{"date-parts":[[2014,7,1]]},"references-count":34,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2014,7]]}},"URL":"https:\/\/doi.org\/10.4018\/jitr.2014070102","relation":{},"ISSN":["1938-7857","1938-7865"],"issn-type":[{"value":"1938-7857","type":"print"},{"value":"1938-7865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,7,1]]}}}