{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T06:02:57Z","timestamp":1672984977802},"reference-count":27,"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":[[2021,8,1]]},"DOI":"10.1587\/transinf.2020bdp0005","type":"journal-article","created":{"date-parts":[[2021,7,31]],"date-time":"2021-07-31T22:14:00Z","timestamp":1627769640000},"page":"1195-1203","source":"Crossref","is-referenced-by-count":0,"title":["Toward Human-Friendly ASR Systems: Recovering Capitalization and Punctuation for Vietnamese Text"],"prefix":"10.1587","volume":"E104.D","author":[{"given":"Thi Thu","family":"HIEN NGUYEN","sequence":"first","affiliation":[{"name":"Thai Nguyen University of Education"}]},{"given":"Thai","family":"BINH NGUYEN","sequence":"additional","affiliation":[{"name":"Vietnam Artificial Intelligence System"}]},{"given":"Ngoc","family":"PHUONG PHAM","sequence":"additional","affiliation":[{"name":"Vietnam Artificial Intelligence System"}]},{"given":"Quoc","family":"TRUONG DO","sequence":"additional","affiliation":[{"name":"Vietnam Artificial Intelligence System"}]},{"given":"Tu","family":"LUC LE","sequence":"additional","affiliation":[{"name":"Office of Hanoi People's Committee"}]},{"given":"Chi","family":"MAI LUONG","sequence":"additional","affiliation":[{"name":"University of Science and Technology of Hanoi"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] L.V. Lita, A. Ittycheriah, S. Roukos, and N. Kambhatla, \u201cTruecasing,\u201d Proceedings of the 41st Annual Meeting on Association for Computational Linguistics-Volume 1, pp.152-159, Association for Computational Linguistics, 2003. 10.3115\/1075096.1075116","DOI":"10.3115\/1075096.1075116"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] C. Chelba and A. Acero, \u201cAdaptation of maximum entropy capitalizer: Little data can help a lot,\u201d Computer Speech & Language, vol.20, no.4, pp.382-399, 2006. 10.1016\/j.csl.2005.05.005","DOI":"10.1016\/j.csl.2005.05.005"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] W. Wang, K. Knight, and D. Marcu, \u201cCapitalizing machine translation,\u201d Proceedings of the Human Language Technology Conference of the NAACL, Main Conference, pp.1-8, 2006. 10.3115\/1220835.1220836","DOI":"10.3115\/1220835.1220836"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] R.H. Susanto, H.L. Chieu, and W. Lu, \u201cLearning to capitalize with character-level recurrent neural networks: an empirical study,\u201d Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp.2090-2095, 2016. 10.18653\/v1\/d16-1225","DOI":"10.18653\/v1\/D16-1225"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] J. Huang and G. Zweig, \u201cMaximum entropy model for punctuation annotation from speech,\u201d Seventh International Conference on Spoken Language Processing, 2002.","DOI":"10.21437\/ICSLP.2002-307"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] O. Tilk and T. Alum\u00e4e, \u201cLstm for punctuation restoration in speech transcripts,\u201d Sixteenth annual conference of the international speech communication association, 2015.","DOI":"10.21437\/Interspeech.2015-240"},{"key":"7","unstructured":"[7] W. Lu and H.T. Ng, \u201cBetter punctuation prediction with dynamic conditional random fields,\u201d Proceedings of the 2010 conference on empirical methods in natural language processing, pp.177-186, 2010."},{"key":"8","unstructured":"[8] N. Ueffing, M. Bisani, and P. Vozila, \u201cImproved models for automatic punctuation prediction for spoken and written text,\u201d Interspeech, pp.3097-3101, 2013."},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] C. Xu, L. Xie, G. Huang, X. Xiao, E.S. Chng, and H. Li, \u201cA deep neural network approach for sentence boundary detection in broadcast news,\u201d Fifteenth annual conference of the international speech communication association, 2014.","DOI":"10.21437\/Interspeech.2014-599"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] O. Tilk and T. Alum\u00e4e, \u201cBidirectional recurrent neural network with attention mechanism for punctuation restoration,\u201d Interspeech, pp.3047-3051, 2016. 10.21437\/interspeech.2016-1517","DOI":"10.21437\/Interspeech.2016-1517"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] A. \u00d6ktem, M. Farr\u00fas, and L. Wanner, \u201cAttentional parallel rnns for generating punctuation in transcribed speech,\u201d International Conference on Statistical Language and Speech Processing, pp.131-142, Springer, 2017. 10.1007\/978-3-319-68456-7_11","DOI":"10.1007\/978-3-319-68456-7_11"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] G. Szasz\u00e1k, \u201cAn audio-based sequential punctuation model for asr and its effect on human readability,\u201d Acta Polytechnica Hungarica, vol.16, no.2, 2019.","DOI":"10.12700\/APH.16.2.2019.2.6"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] M.\u00c1. T\u00fcndik, B. Tarj\u00e1n, and G. Szasz\u00e1k, \u201cA bilingual comparison of maxent-and rnn-based punctuation restoration in speech transcripts,\u201d 2017 8th IEEE International Conference on Cognitive Infocommunications (CogInfoCom), pp.000121-000126, IEEE, 2017. 10.1109\/coginfocom.2017.8268227","DOI":"10.1109\/CogInfoCom.2017.8268227"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] M.\u00c1. T\u00fcndik and G. Szasz\u00e1k, \u201cJoint word-and character-level embedding cnn-rnn models for punctuation restoration,\u201d 2018 9th IEEE International Conference on Cognitive Infocommunications (CogInfoCom), pp.000135-000140, IEEE, 2018. 10.1109\/coginfocom.2018.8639876","DOI":"10.1109\/CogInfoCom.2018.8639876"},{"key":"15","unstructured":"[15] H. Christensen, Y. Gotoh, and S. Renals, \u201cPunctuation annotation using statistical prosody models,\u201d ISCA Workshop on Prosody in Speech Recognition and Understanding, 2001."},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] A. Gravano, M. Jansche, and M. Bacchiani, \u201cRestoring punctuation and capitalization in transcribed speech,\u201d 2009 IEEE International Conference on Acoustics, Speech and Signal Processing, pp.4741-4744, IEEE, 2009. 10.1109\/icassp.2009.4960690","DOI":"10.1109\/ICASSP.2009.4960690"},{"key":"17","unstructured":"[17] A. Caranica, H. Cucu, A. Buzo, and C. Burileanu, \u201cCapitalization and punctuation restoration for romanian language,\u201d University \u201cPolitehnica\u201d of Bucharest Scientific Bulletin, vol.77, no.3, 2015."},{"key":"18","doi-asserted-by":"publisher","unstructured":"[18] F. Batista, H. Moniz, I. Trancoso, and N. Mamede, \u201cBilingual experiments on automatic recovery of capitalization and punctuation of automatic speech transcripts,\u201d IEEE Trans. Audio, Speech, Language Process., vol.20, no.2, pp.474-485, 2012. 10.1109\/tasl.2011.2159594","DOI":"10.1109\/TASL.2011.2159594"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] A. V\u0101ravs and A. Salimbajevs, \u201cRestoring punctuation and capitalization using transformer models,\u201d International Conference on Statistical Language and Speech Processing, pp.91-102, Springer, 2018. 10.1007\/978-3-030-00810-9_9","DOI":"10.1007\/978-3-030-00810-9_9"},{"key":"20","unstructured":"[20] J. Devlin, M.W. Chang, K. Lee, and K. Toutanova, \u201cBert: Pre-training of deep bidirectional transformers for language understanding,\u201d arXiv preprint arXiv:1810.04805, 2018."},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] S. Tripathi, C. Singh, A. Kumar, C. Pandey, and N. Jain, \u201cBidirectional transformer based multi-task learning for natural language understanding,\u201d International Conference on Applications of Natural Language to Information Systems, pp.54-65, Springer, 2019. 10.1007\/978-3-030-23281-8_5","DOI":"10.1007\/978-3-030-23281-8_5"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] M. Arkhipov, M. Trofimova, Y. Kuratov, and A. Sorokin, \u201cTuning multilingual transformers for language-specific named entity recognition,\u201d Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing, pp.89-93, 2019. 10.18653\/v1\/w19-3712","DOI":"10.18653\/v1\/W19-3712"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] L. Zhang and H. Wang, \u201cUsing bidirectional transformer-crf for spoken language understanding,\u201d CCF International Conference on Natural Language Processing and Chinese Computing, pp.130-141, Springer, 2019. 10.1007\/978-3-030-32233-5_11","DOI":"10.1007\/978-3-030-32233-5_11"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] B. Nguyen, V.B.H. Nguyen, H. Nguyen, P.N. Phuong, T.-L. Nguyen, Q.T. Do, and L.C. Mai, \u201cFast and accurate capitalization and punctuation for automatic speech recognition using transformer and chunk merging,\u201d 2019 22nd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA), pp.1-5, IEEE, 2019. 10.1109\/o-cocosda46868.2019.9041202","DOI":"10.1109\/O-COCOSDA46868.2019.9041202"},{"key":"25","unstructured":"[25] H.N.T. Thu, B.N. Thai, H.N.V. Bao, T.D. Quoc, M.L. Chi, and H.N.T. Minh, \u201cRecovering capitalization for automatic speech recognition of vietnamese using transformer and chunk merging,\u201d 2019 11th International Conference on Knowledge and Systems Engineering (KSE), pp.1-5, IEEE, 2019. 10.1109\/kse.2019.8919342"},{"key":"26","unstructured":"[26] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, \u0141. Kaiser, and I. Polosukhin, \u201cAttention is all you need,\u201d Advances in neural information processing systems, pp.5998-6008, 2017."},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] M. Ott, S. Edunov, A. Baevski, A. Fan, S. Gross, N. Ng, D. Grangier, and M. Auli, \u201cfairseq: A fast, extensible toolkit for sequence modeling,\u201d Proceedings of NAACL-HLT 2019: Demonstrations, pp.48-53, 2019. 10.18653\/v1\/n19-4009","DOI":"10.18653\/v1\/N19-4009"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E104.D\/8\/E104.D_2020BDP0005\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T01:35:45Z","timestamp":1672968945000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E104.D\/8\/E104.D_2020BDP0005\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,1]]},"references-count":27,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2021]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2020bdp0005","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,1]]},"article-number":"2020BDP0005"}}