{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T09:50:54Z","timestamp":1764841854886,"version":"3.37.3"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2016,9,1]],"date-time":"2016-09-01T00:00:00Z","timestamp":1472688000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2016,9]]},"DOI":"10.1109\/taslp.2016.2562505","type":"journal-article","created":{"date-parts":[[2016,5,3]],"date-time":"2016-05-03T18:20:17Z","timestamp":1462299617000},"page":"1524-1534","source":"Crossref","is-referenced-by-count":10,"title":["Semi-Supervised Acoustic Model Training by Discriminative Data Selection From Multiple ASR Systems\u2019 Hypotheses"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7636-3797","authenticated-orcid":false,"given":"Sheng","family":"Li","sequence":"first","affiliation":[]},{"given":"Yuya","family":"Akita","sequence":"additional","affiliation":[]},{"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"A practical guide to training restricted Boltzmann machines","year":"2010","author":"hinton","key":"ref39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref33","first-page":"3526","article-title":"Discriminative data selection for lightly supervised training of acoustic model using closed caption texts","author":"li","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0186"},{"article-title":"CRF-based combination of contextual features to improve a posteriori word level confidence measures","year":"0","author":"fayolle","key":"ref31"},{"article-title":"Combining information sources for confidence estimation with CRF models","year":"0","author":"seigel","key":"ref30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.659110"},{"article-title":"Ensemble deep learning for speech recognition","year":"0","author":"deng","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2303295"},{"article-title":"Posterior probability decoding, confidence estimation and system combination","year":"0","author":"evermann","key":"ref60"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.03.004"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854214"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3115\/1614108.1614125"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2000.0138"},{"key":"ref64","first-page":"232","article-title":"iCNC and iROVER: The limits of improving system combination with classification?","author":"hoffmeister","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495100"},{"article-title":"On the use of a multilingual neural network front-end","year":"0","author":"scanzio","key":"ref65"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424246"},{"key":"ref29","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","author":"lafferty","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2141988"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.828641"},{"key":"ref1","first-page":"7","article-title":"Corpus of spontaneous Japanese: Its design and evaluation","author":"maekawa","year":"0","journal-title":"Proc IEEE ISCA IEEE Workshop Spontaneous Speech Process Recog"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078570"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.12.004"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854213"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/89.906002"},{"key":"ref23","first-page":"827","article-title":"Estimating confidence using word lattices","volume":"2","author":"kemp","year":"0","journal-title":"Proc EUROSPEECH"},{"key":"ref26","first-page":"495","article-title":"Finding consensus among words: Lattice-based word error minimization","author":"mangu","year":"0","journal-title":"Proc EUROSPEECH"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326105"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1121\/1.4768800"},{"article-title":"Investigation on mandarin broadcast news speech recognition","year":"0","author":"hwang","key":"ref51"},{"key":"ref59","first-page":"831","article-title":"Improved estimation, evaluation and applications of confidence measures for speech recognition","author":"siu","year":"0","journal-title":"Proc EUROSPEECH"},{"key":"ref58","first-page":"1022","article-title":"Multi-interval discretization of continuous attributes for classification learning","author":"fayyad","year":"0","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.2307\/2006193"},{"key":"ref56","first-page":"1035","article-title":"Efficient on-the-fly hypothesis rescoring in a hybrid GPU\/CPU-based large vocabulary continuous speech recognition engine","author":"kim","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854012"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2042"},{"key":"ref53","first-page":"211","article-title":"Discriminative joint modeling of lexical variation and acoustic confusion for automated narrative retelling assessment","author":"lehr","year":"0","journal-title":"Proc Conf North Amer Chapt Assoc Comput Linguist"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639104"},{"key":"ref10","first-page":"2360","article-title":"Semi–supervised GMM and DNN acoustic model training with multi-system combination and confidence re-calibration","author":"huang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707741"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854014"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078564"},{"article-title":"Multi-softmax deep neural network for semi-supervised training","year":"0","author":"su","key":"ref14"},{"article-title":"Semi-supervised maximum mutual information training of deep neural network acoustic models","year":"0","author":"manohar","key":"ref15"},{"article-title":"IARPA babel program","year":"2014","author":"harper","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639348"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639081"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638959"},{"key":"ref4","first-page":"2553","article-title":"Recent progress in the MIT spoken lecture processing project","author":"glass","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref3","first-page":"281","article-title":"Recognition of classroom lectures in European Portuguese","author":"trancoso","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref6","first-page":"4929","article-title":"Automatic lecture transcription by exploiting slide information for language model adaptation","author":"kawahara","year":"0","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref5","first-page":"2349","article-title":"Dynamic language model adaptation using presentation slides for lecture speech recognition","author":"yamazaki","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.02.014"},{"key":"ref7","first-page":"3","article-title":"Overview of the IWSLT 2010","author":"paul","year":"0","journal-title":"Evaluation Campaign Proc Int Workshop Spoken Language Translation"},{"key":"ref49","first-page":"4325","article-title":"Modeling characters versus words for mandarin speech recognition","author":"luo","year":"0","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707758"},{"article-title":"The Kaldi speech recognition toolkit","year":"0","author":"povey","key":"ref46"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960682"},{"article-title":"Fast speaker normalization and adaptation based on BIC for meeting speech recognition","year":"0","author":"mimura","key":"ref48"},{"key":"ref47","first-page":"131","article-title":"Recent development of open-source speech recognition engine Julius","author":"lee","year":"0","journal-title":"Proc Asia-Pacific Signal Inform Process Assoc Annu Summit Conf"},{"article-title":"Sequence-discriminative training of deep neural networks","year":"0","author":"vesely","key":"ref42"},{"key":"ref41","first-page":"6664","article-title":"Error back propagation for sequence training of context-dependent deep neural networks for conversational speech transcription","author":"su","year":"0","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref44","first-page":"2781","article-title":"A comparative study on speech summarization of broadcast news and lecture speech","author":"zhang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2014.6936595"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7497021\/07464281.pdf?arnumber=7464281","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:11:45Z","timestamp":1642003905000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7464281\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,9]]},"references-count":67,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2016.2562505","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2016,9]]}}}