{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T05:46:44Z","timestamp":1751348804426,"version":"3.41.0"},"reference-count":29,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"8","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2015]]},"DOI":"10.1587\/transinf.2015edp7047","type":"journal-article","created":{"date-parts":[[2015,7,31]],"date-time":"2015-07-31T22:42:28Z","timestamp":1438382548000},"page":"1545-1552","source":"Crossref","is-referenced-by-count":1,"title":["Automatic Lecture Transcription Based on Discriminative Data Selection for Lightly Supervised Acoustic Model Training"],"prefix":"10.1587","volume":"E98.D","author":[{"given":"Sheng","family":"LI","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Kyoto University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuya","family":"AKITA","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Kyoto University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"KAWAHARA","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Kyoto University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","unstructured":"[1] K. Maekawa, \u201cCorpus of Spontaneous Japanese: Its Design and Evaluation,\u201d Proc. ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition, pp.7-12, 2003."},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] H. Nanjo and T. Kawahara, \u201cLanguage Model and Speaking Rate Adaptation for Spontaneous Presentation Speech Recognition,\u201d IEEE-TSAP, vol.12, no.4, pp.391-400, 2004.","DOI":"10.1109\/TSA.2004.828641"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] I. Trancoso, R. Nunes, L. Neves, C. Viana, H. Moniz, D. Caseiro, and A.I. Mata, \u201cRecognition of Classroom Lectures in European Portuguese,\u201d Proc. INTERSPEECH, pp.281-284, 2006.","DOI":"10.21437\/Interspeech.2006-88"},{"key":"4","unstructured":"[4] J. Glass, T.J. Hazen, S. Cyphers, I. Malioutov, D. Huynh, and R. Barzilay, \u201cRecent Progress in the MIT Spoken Lecture Processing Project,\u201d Proc. INTERSPEECH, pp.2553-2556, 2007."},{"key":"5","unstructured":"[5] H. Yamazaki, K. Iwano, K. Shinoda, S. Furui, and H. Yokota, \u201cDynamic Language Model Adaptation Using Presentation Slides for Lecture Speech Recognition,\u201d Proc. INTERSPEECH, pp.2349-2352, 2007."},{"key":"6","unstructured":"[6] T. Kawahara, Y. Nemoto, and Y. Akita, \u201cAutomatic Lecture Transcription by Exploiting Slide Information for Language Model Adaptation,\u201d Proc. ICASSP, pp.4929-4932, 2008."},{"key":"7","unstructured":"[7] M. Paul, M. Federico, and S. Stucker, \u201cOverview of the IWSLT 2010 Evaluation Campaign,\u201d Proc. IWSLT, pp.3-27, 2010."},{"key":"8","unstructured":"[8] J. Zhang, H. Chan, P. Fung, and L. Cao, \u201cA Comparative Study on Speech Summarization of Broadcast News and Lecture Speech,\u201d Proc. INTERSPEECH, pp.2781-2784, 2007."},{"key":"9","unstructured":"[9] S.-Y. Kong, M.-R. Wu, C.-K. Lin, Y.-S. Fu, and L.-S. Lee, \u201cLearning on Demand-Course Lecture Distillation by Information Extraction and Semantic Structuring for Spoken Documents,\u201d Proc. INTERSPEECH, pp.4709-4712, 2009."},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] L. Lamel, J.-L. Gauvain, and G. Adda, \u201cLightly Supervised and Unsupervised Acoustic Model Training,\u201d Computer Speech & Language, vol.16, no.1, pp.115-129, Jan. 2002.","DOI":"10.1006\/csla.2001.0186"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] L. Nguyen and B. Xiang, \u201cLight Supervision in Acoustic Model Training,\u201d Proc. ICASSP, vol.1, p.I-185, 2004.","DOI":"10.1109\/ICASSP.2004.1325953"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] H.Y. Chan and P. Woodland, \u201cImproving Broadcast News Transcription by Lightly Supervised Discriminative Training,\u201d Proc. ICASSP, vol.1, pp.737-740, 2004.","DOI":"10.1109\/ICASSP.2004.1326091"},{"key":"13","unstructured":"[13] T. Kawahara, M. Mimura, and Y. Akita, \u201cLanguage Model Transformation Applied to Lightly Supervised Training of Acoustic Model for Congress Meetings,\u201d Proc. ICASSP, pp.3853-3856, 2009."},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] Y. Long, M.J.F. Gales, P. Lanchantin, X. Liu, M.S. Seigel, and P.C. Woodland, \u201cImproving Lightly Supervised Training for Broadcast Transcription,\u201d Proc. INTERSPEECH, 2013.","DOI":"10.21437\/Interspeech.2013-516"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] J. Driesen and S. Renals, \u201cLightly supervised automatic subtitling of weather forecasts,\u201d Proc. IEEE-ASRU, pp.452-457, 2013.","DOI":"10.1109\/ASRU.2013.6707772"},{"key":"16","unstructured":"[16] A. Lee and T. Kawahara, \u201cRecent development of open-source speech recognition engine Julius,\u201d Proc. APSIPA ASC, pp.131-137, 2009."},{"key":"17","unstructured":"[17] J. Lafferty, A. McCallum, and F. Pereira, \u201cConditional random fields: Probabilistic models for segmenting and labeling sequence data,\u201d Proc. ICML, 2001."},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] M. Seigel and P. Woodland, \u201cCombining Information Sources for Confidence Estimation with CRF Models,\u201d Proc. INTERSPEECH, 2011.","DOI":"10.21437\/Interspeech.2011-352"},{"key":"19","unstructured":"[19] W. Chen, S. Ananathakrishnan, R. Kumar, R. Prasad, and P. Natarajan, \u201cASR error dection in a conversational spoken language translation system,\u201d Proc. ICASSP, pp.7418-7422, 2013."},{"key":"20","unstructured":"[20] M. Lehr, I. Shafran, E. Prud'hommeaux, and B. Roark, \u201cDiscriminative Joint Modeling of Lexical Variation and Acoustic Confusion for Automated Narrative Retelling Assessment,\u201d Proc. NAACL, 2013."},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] H. Jiang, \u201cConfidence measures for speech recognition: A survey,\u201d Speech Communication, vol.45, no.4, pp.455-470, April 2005.","DOI":"10.1016\/j.specom.2004.12.004"},{"key":"22","unstructured":"[22] H. Lin, and J. Bilmes, \u201cHow to select a good training-data subset for transcription: submodular active selection for sequences,\u201d Proc. INTERSPEECH, pp.2859-2862, 2009."},{"key":"23","unstructured":"[23] M. Mimura and T. Kawahara, \u201cFast Speaker Normalization and Adaptation Based on BIC for Meeting Speech Recognition,\u201d Proc. APSIPA, 2011."},{"key":"24","unstructured":"[24] T. Lavergne, O. Capp\u00e9, and F. Yvon, \u201cPractical Very Large Scale CRFs,\u201d Proc. ACL, pp.504-513, July 2010."},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] N. Sokolovska, T. Lavergne, O. Capp\u00e9, and F. Yvon, \u201cEfficient Learning of Sparse Conditional Random Fields for Supervised Sequence Labelling,\u201d IEEE J. Sel. Topics Signal Process., vol.4, no.6, pp.953-964, Dec. 2010.","DOI":"10.1109\/JSTSP.2010.2076150"},{"key":"26","unstructured":"[26] D. Povey, A. Ghoshal, G. Boulianne, L. Burget, O. Glembek, N. Goel, M. Hannemann, P. Motlicek, Y. Qian, P. Schwarz, J. Silovsky, G. Stemmer, and K. Vesely, \u201cThe Kaldi speech recognition toolkit,\u201d IEEE-ASRU, 2011."},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] S. Li, and L. Wang, \u201cCross Linguistic Comparison of Mandarin and English EMA Articulatory Data,\u201d Proc. INTERSPEECH, 2012.","DOI":"10.21437\/Interspeech.2012-272"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] A. Lee, K. Shikano, and T. Kawahara, \u201cReal-time word confidence scoring using local posterior probabilities on tree trellis search,\u201d Proc. IEEE-ICASSP, vol.1, pp.793-796, 2004.","DOI":"10.1109\/ICASSP.2004.1326105"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] S. Li, Y. Akita, and T. Kawahara, \u201cCorpus and transcription system of Chinese lecture room,\u201d Proc. Chinese Spoken Language Processing (ISCSLP), pp.442-445, 2014.","DOI":"10.1109\/ISCSLP.2014.6936595"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E98.D\/8\/E98.D_2015EDP7047\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T20:57:52Z","timestamp":1748552272000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E98.D\/8\/E98.D_2015EDP7047\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"references-count":29,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2015]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2015edp7047","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"type":"print","value":"0916-8532"},{"type":"electronic","value":"1745-1361"}],"subject":[],"published":{"date-parts":[[2015]]}}}