{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T14:56:44Z","timestamp":1778943404582,"version":"3.51.4"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2017,5,8]],"date-time":"2017-05-08T00:00:00Z","timestamp":1494201600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Ministry of Science and Technology, Taiwan (TW)","award":["105-2221-E-006 -161 -MY3"],"award-info":[{"award-number":["105-2221-E-006 -161 -MY3"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1186\/s13636-017-0107-3","type":"journal-article","created":{"date-parts":[[2017,5,8]],"date-time":"2017-05-08T13:21:48Z","timestamp":1494249708000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Miscommunication handling in spoken dialog systems based on error-aware dialog state detection"],"prefix":"10.1186","volume":"2017","author":[{"given":"Chung-Hsien","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming-Hsiang","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Bin","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,5,8]]},"reference":[{"key":"107_CR1","doi-asserted-by":"crossref","unstructured":"JR Bellegarda, in Spoken language understanding for natural interaction: the siri experience, eds. by J. R. S. G. M. a. D. L. Mariani. Natural Interaction with Robots, Knowbots and Smartphones, (Springer, New York, 2014), pp. 3\u201314","DOI":"10.1007\/978-1-4614-8280-2_1"},{"key":"107_CR2","doi-asserted-by":"crossref","unstructured":"KP Engelbrecht, in A user model for dialog system evaluation based on activation of subgoals, eds. J. Mariani, S. Rosset, M. Garnier-Rizet and L. Devillers. Natural Interaction with Robots, Knowbots and Smartphones (Springer, New York, 2014), pp. 363\u2013374","DOI":"10.1007\/978-1-4614-8280-2_33"},{"key":"107_CR3","doi-asserted-by":"crossref","unstructured":"J. a. J. F Henderson, in Data-driven methods for spoken language understanding, eds. O. Lemon and O. Pietquin. Data-Driven Methods for Adaptive Spoken Dialogue Systems (Springer, New York, 2012), pp. 19\u201338","DOI":"10.1007\/978-1-4614-4803-7_3"},{"key":"107_CR4","doi-asserted-by":"crossref","unstructured":"S Kim, LF D\u2019Haro, RE Banchs, JD Williams, M Henderson, J Williams, in Proceedings of the 7th International Workshop on Spoken Dialogue Systems (IWSDS). The fourth dialog state tracking challenge, 1\u201314 2016","DOI":"10.1109\/SLT.2016.7846311"},{"issue":"3","key":"107_CR5","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1017\/S1351324900002539","volume":"6","author":"S Larsson","year":"2000","unstructured":"S Larsson, DR Traum, Information state and dialogue management in the TRINDI dialogue move engine toolkit. Natural Language Engineering 6(3), 323\u2013340 (2000)","journal-title":"Natural Language Engineering"},{"key":"107_CR6","volume-title":"RavenClaw: Dialog management using hierarchical task decomposition and an expectation agenda","author":"D Bohus","year":"2003","unstructured":"D Bohus, AI Rudnicky, Proceedings of Eighth European Conference on Speech Communication and Technology, in RavenClaw: Dialog management using hierarchical task decomposition and an expectation agenda, 2003"},{"key":"107_CR7","unstructured":"T Paek, E Horvitz, in Proceedings of the Sixteenth conference on Uncertainty in artificial intelligence. Conversation as action under uncertainty, (Morgan Kaufmann Publishers Inc, 2000), pp. 455\u2013464"},{"issue":"2","key":"107_CR8","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1016\/j.csl.2006.06.008","volume":"21","author":"JD Williams","year":"2007","unstructured":"JD Williams, S Young, Partially observable Markov decision processes for spoken dialog systems. Computer Speech & Language 21(2), 393\u2013422 (2007)","journal-title":"Computer Speech & Language"},{"key":"107_CR9","volume-title":"A \u2018K hypotheses+ other\u2019 belief updating model","author":"D Bohus","year":"2006","unstructured":"D Bohus, A Rudnick, Proceedings of the AAAI Workshop on Statistical and Empirical Methods in Spoken Dialogue Systems, in A \u2018K hypotheses+ other\u2019 belief updating model, 2006"},{"key":"107_CR10","first-page":"1","volume-title":"Dialogue state tracking using long short term memory neural networks","author":"K Yoshino","year":"2016","unstructured":"K Yoshino, T Hiraoka, G Neubig, S Nakamura, Proceedings of the Seventh International Workshop on Spoken Dialog Systems (IWSDS), in Dialogue state tracking using long short term memory neural networks, 2016, pp. 1\u20138"},{"issue":"1","key":"107_CR11","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1109\/89.817460","volume":"8","author":"V Zue","year":"2000","unstructured":"V Zue, S Seneff, J Glass, J Polifroni, C Pao, T Hazen, L Hetherington, JUPlTER: a telephone-based conversational interface for weather information. IEEE Transactions on Speech and Audio Processing 8(1), 85\u201396 (2000)","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"107_CR12","volume-title":"Machine learning for dialog state tracking: a review","author":"M Henderson","year":"2015","unstructured":"M Henderson, Proceedings of the First International Workshop on Machine Learning in Spoken Language Processing, in Machine learning for dialog state tracking: a review, 2015"},{"issue":"5","key":"107_CR13","doi-asserted-by":"publisher","first-page":"979","DOI":"10.1109\/TASL.2014.2315271","volume":"22","author":"V Rieser","year":"2014","unstructured":"V Rieser, O Lemon, S Keizer, Natural language generation as incremental planning under uncertainty: adaptive information presentation for statistical dialogue systems. IEEE Transactions on Audio, Speech and Language Processing 22(5), 979\u2013994 (2014)","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"107_CR14","doi-asserted-by":"publisher","unstructured":"HH Clark, Using language, (Cambridge University Press, Cambridge, 1996)","DOI":"10.1017\/CBO9780511620539"},{"key":"107_CR15","first-page":"1","volume-title":"Recovering from non-understanding errors in a conversational dialogue system","author":"M Henderson","year":"2012","unstructured":"M Henderson, C Matheson, J Oberlander, Proceedings of SemDial 2012 (SeineDial): The 16th Workshop on the Semantics and Pragmatics of Dialogue, in Recovering from non-understanding errors in a conversational dialogue system, 2012, pp. 1\u20138"},{"key":"107_CR16","unstructured":"H Bunt, in Proceedings of THINK Quarterly. Context and dialog control, 3(1) 19\u201331 (1994)"},{"key":"107_CR17","first-page":"162","volume-title":"Training a dialog act tagger for human-human and human-computer travel dialogs","author":"R Prasad","year":"2002","unstructured":"R Prasad, M Walker, Proceedings of Annual Meeting of the Association for Computational Linguistics (ACL), in Training a dialog act tagger for human-human and human-computer travel dialogs, 2002, pp. 162\u2013173"},{"key":"107_CR18","first-page":"439","volume-title":"Is it harder to parse Chinese, or the Chinese treebank? (Association for Computational Linguistics","author":"R Levy","year":"2003","unstructured":"R Levy, C Manning, Proceedings of the 41st Annual Meeting on Association for Computational Linguistics-Volume 1, in Is it harder to parse Chinese, or the Chinese treebank? (Association for Computational Linguistics, 2003), pp. 439\u2013446"},{"key":"107_CR19","first-page":"1043","volume-title":"Semantic role labeling with discriminative feature selection for spoken language understanding","author":"C-H Liu","year":"2009","unstructured":"C-H Liu, C-H Wu, Proceedings of Interspeech, in Semantic role labeling with discriminative feature selection for spoken language understanding, 2009, pp. 1043\u20131046"},{"key":"107_CR20","first-page":"85","volume-title":"Shallow semantic parsing for spoken language understanding","author":"B Coppola","year":"2009","unstructured":"B Coppola, A Moschitti, G Riccardi, Proceedings of NAACL-HLT, in Shallow semantic parsing for spoken language understanding, 2009, pp. 85\u201388"},{"key":"107_CR21","volume-title":"Proceedings of ICSLP, Automatic utterance type detection using supra segmental features","author":"H Wright","year":"1998","unstructured":"H Wright, Proceedings of ICSLP, Automatic utterance type detection using supra segmental features, 1998"},{"issue":"3","key":"107_CR22","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1162\/089120100561737","volume":"26","author":"A Stolcke","year":"2000","unstructured":"A Stolcke, N Coccaro, R Bates, P Taylor, C Van Ess-Dykema, K Ries, E Shriberg, D Jurafsky, R Martin, M Meteer, Dialogue act modeling for automatic tagging and recognition of conversational speech. Computational Linguistics 26(3), 339\u2013373 (2000)","journal-title":"Computational Linguistics"},{"issue":"6","key":"107_CR23","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1109\/89.725322","volume":"6","author":"T Kawahara","year":"1998","unstructured":"T Kawahara, C-H Lee, B-H Juang, Flexible speech understanding based on combined key-phrase detection and verification. IEEE Transactions on Speech and Audio Processing 6(6), 558\u2013568 (1998)","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"107_CR24","volume-title":"Dialog management using weighted finite-state transducers","author":"C Hori","year":"2008","unstructured":"C Hori, K Ohtake, T Misu, H Kashioka, S Nakamura, Proceedings of Interspeech, in Dialog management using weighted finite-state transducers, 2008"},{"key":"107_CR25","volume-title":"Reinforcement learning: an introduction","author":"AG Barto","year":"1998","unstructured":"AG Barto, Reinforcement learning: an introduction (MIT Press, London, 1998)"},{"key":"107_CR26","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1613\/jair.859","volume":"16","author":"S Singh","year":"2002","unstructured":"S Singh, D Litman, M Kearns, M Walker, Optimizing dialog management with reinforcement learning: experiments with the NJFun system. Journal of Artificial Intelligence Research 16, 105\u2013133 (2002)","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"5","key":"107_CR27","doi-asserted-by":"publisher","first-page":"1574","DOI":"10.1109\/TASL.2006.878267","volume":"14","author":"J-F Yeh","year":"2006","unstructured":"J-F Yeh, C-H Wu, Edit disfluency detection and correction using a cleanup language model and an alignment model. IEEE Transactions on Speech and Audio Processing 14(5), 1574\u20131583 (2006)","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"6","key":"107_CR28","first-page":"6","volume":"10","author":"C-H Wu","year":"2010","unstructured":"C-H Wu, W-B Liang, J-F Yeh, Interruption point detection of spontaneous speech using inter-syllable boundary based prosodic features. ACM Transaction on Asian Language Information Processing 10(6), 6\u20131-6:21 (2010)","journal-title":"ACM Transaction on Asian Language Information Processing"},{"key":"107_CR29","first-page":"225","volume-title":"Recognition of syllable-contracted words in spontaneous speech using word expansion and duration information","author":"W-B Liang","year":"2008","unstructured":"W-B Liang, C-H Wu, Y-K Kang, Proceedings of ISCSLP, in Recognition of syllable-contracted words in spontaneous speech using word expansion and duration information, 2008, pp. 225\u2013228"},{"key":"107_CR30","unstructured":"G Skantze, Error handling in spoken dialog systems\u2014managing uncertainty, grounding z and miscommunication. (Doctoral Thesis, 2007)"},{"key":"107_CR31","volume-title":"Doing research on a deployed spoken dialog system: one year of let\u2019s go! experience","author":"A Raux","year":"2006","unstructured":"A Raux, D Bohus, B Langner, AW Black, M Eskenazi, Proceedings of Interspeech, in Doing research on a deployed spoken dialog system: one year of let\u2019s go! experience, 2006"},{"key":"107_CR32","first-page":"438","volume-title":"Ontology-based grounding of spoken language understanding","author":"S Quarteroni","year":"2009","unstructured":"S Quarteroni, M Dinarelli, G Riccardi, Proceedings of IEEE Workshop on Automatic Speech Recognition & Understanding, in Ontology-based grounding of spoken language understanding, 2009, pp. 438\u2013443"},{"issue":"2","key":"107_CR33","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1016\/j.csl.2009.04.001","volume":"24","author":"S Young","year":"2010","unstructured":"S Young, M Gasic, S Keizer, F Mairesse, J Schatzmann, B Thomson, K Yu, The hidden information state model: a practical framework for POMDP-based spoken dialog management. Computer Speech & Language 24(2), 150\u2013174 (2010)","journal-title":"Computer Speech & Language"},{"issue":"2","key":"107_CR34","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1207\/s15516709cog1302_7","volume":"13","author":"HH Clark","year":"1989","unstructured":"HH Clark, EF Schaefer, Contributing to discourse. Cognitive Science 13(2), 259\u2013294 (1989)","journal-title":"Cognitive Science"},{"key":"107_CR35","unstructured":"The Stanford Parser: A statistical parser, http:\/\/nlp.stanford.edu\/software\/lex-parser.shtml . Accessed 8 Dec 2016"},{"key":"107_CR36","unstructured":"SJ Young, D Kershaw, J Odell, D, Ollason, V Valt-chev, P Woodl, The HTK Book, version 3.4. (Cambridge University Press, Cambridge, 2009)"},{"key":"107_CR37","unstructured":"S Young, G Evermann, D Kershaw, G Moore, J Odell, D Ollason, V Valtchev, P Woodland, in Handbook of the HTK book, vol 3 (Cambridge University Engineering Department, Cambridge, 2002), p. 175."},{"key":"107_CR38","doi-asserted-by":"crossref","unstructured":"International Phonetic Association (IPA), Handbook of the International Phonetic Association: a guide to the use of the International Phonetic Alphabet. (Cambridge University Press, Cambridge, 1999)","DOI":"10.1017\/9780511807954"},{"key":"107_CR39","first-page":"901","volume-title":"SRILM\u2014an extensible language modeling toolkit","author":"A Stolcke","year":"2002","unstructured":"A Stolcke, Proceedings of International Conference on Spoken Language Processing, in SRILM\u2014an extensible language modeling toolkit, 2002, pp. 901\u2013904"},{"key":"107_CR40","first-page":"78","volume-title":"Estimation method of user satisfaction using N-gram-based dialog history model for spoken dialog system","author":"S Hara","year":"2010","unstructured":"S Hara, N Kitaoka, K Takeda, Proceedings of LREC2010, in Estimation method of user satisfaction using N-gram-based dialog history model for spoken dialog system, 2010, pp. 78\u201383"},{"key":"107_CR41","first-page":"603","volume-title":"Semantic information and derivation rules for robust dialog act detection in a spoken dialog system","author":"W-B Liang","year":"2011","unstructured":"W-B Liang, C-H Wu, C-P Chen, Proceedings of 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers-Volume 2, in Semantic information and derivation rules for robust dialog act detection in a spoken dialog system, 2011, pp. 603\u2013608"},{"key":"107_CR42","first-page":"1","volume":"1","author":"C-P Chen","year":"2012","unstructured":"C-P Chen, C-H Wu, W-B Liang, Robust dialogue act detection based on partial sentence tree, derivation rule, and spectral clustering algorithm. EURASIP Journal on Audio, Speech, and Music Processing 1, 1\u20139 (2012)","journal-title":"EURASIP Journal on Audio, Speech, and Music Processing"},{"key":"107_CR43","unstructured":"D Bohus, Error awareness and recovery in conversational spoken language interfaces. (Doctoral dissertation, SRI International, Carnegie Mellon University, Pittsburgh, CS-07-124, 2007)"},{"key":"107_CR44","first-page":"3034","volume-title":"Automatic detection of task-incompleted dialog for spoken dialog system based on dialog act N-gram","author":"S Hara","year":"2010","unstructured":"S Hara, N Kitaoka, K Takeda, Proceedings of 11th Annual Conference of the International Speech Communication Association (Interspeech), in Automatic detection of task-incompleted dialog for spoken dialog system based on dialog act N-gram, 2010, pp. 3034\u20133037"},{"issue":"1","key":"107_CR45","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1109\/TSA.2005.852992","volume":"14","author":"C-H Wu","year":"2006","unstructured":"C-H Wu, Y-H Chiu, C-J Shia, C-Y Lin, Automatic segmentation and identification of mixed-language speech using delta-BIC and LSA-based GMMs. IEEE Transactions on Audio, Speech and Language Processing 14(1), 266\u2013276 (2006)","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"8","key":"107_CR46","doi-asserted-by":"publisher","first-page":"1279","DOI":"10.1109\/5.880084","volume":"88","author":"JR Bellegarda","year":"2000","unstructured":"JR Bellegarda, Exploiting latent semantic information in statistical language modeling. Proceedings of the IEEE 88(8), 1279\u20131296 (2000)","journal-title":"Proceedings of the IEEE"},{"issue":"5","key":"107_CR47","doi-asserted-by":"publisher","first-page":"1160","DOI":"10.1109\/JPROC.2012.2225812","volume":"101","author":"S Young","year":"2013","unstructured":"S Young, M Gasic, B Thomson, JD Williams, POMDP-based statistical spoken dialog systems: a review. Proceedings of the IEEE 101(5), 1160\u20131179 (2013)","journal-title":"Proceedings of the IEEE"},{"key":"107_CR48","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1613\/jair.1659","volume":"24","author":"MT Spaan","year":"2005","unstructured":"MT Spaan, N Vlassis, Perseus: randomized point-based value iteration for POMDPs. Journal of Artificial Intelligence Research 24, 195\u2013220 (2005)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"107_CR49","unstructured":"V Cherkassky, F Mulier, Learning from data: concept, theory, and methods. (John Wuley & Sons, Inc., Hoboken, 1998)"},{"key":"107_CR50","doi-asserted-by":"crossref","unstructured":"M Vacher, B Lecouteux, JS Romero, M Ajili, F Portet, S Rossato, in Proceedings of the International Conference on Speech Technology and Human-Computer Dialogue. Speech and speaker recognition for home automation: preliminary results, (IEEE, Bucharest, 2015), pp. 1\u201310","DOI":"10.1109\/SPED.2015.7343100"},{"issue":"3","key":"107_CR51","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1016\/S0167-6393(00)00016-9","volume":"33","author":"C-H Wu","year":"2001","unstructured":"C-H Wu, Y-J Chen, Multi-keyword spotting of telephone speech using a fuzzy search algorithm and keyword-driven two-level CBSM. Speech Communication 33(3), 197\u2013212 (2001)","journal-title":"Speech Communication"},{"key":"107_CR52","doi-asserted-by":"crossref","unstructured":"K Ohtake, T Misu, C Hori, H Kashioka S Nakamura, in Proceedings of Second International Symposium on Universal Communication (ISUC'08). Dialogue act annotation for statistically managed spoken dialogue systems, (IEEE, Osaka, 2008), pp. 416\u2013422","DOI":"10.1109\/ISUC.2008.52"}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-017-0107-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13636-017-0107-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-017-0107-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,24]],"date-time":"2024-06-24T00:12:44Z","timestamp":1719187964000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13636-017-0107-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5,8]]},"references-count":52,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,12]]}},"alternative-id":["107"],"URL":"https:\/\/doi.org\/10.1186\/s13636-017-0107-3","relation":{},"ISSN":["1687-4722"],"issn-type":[{"value":"1687-4722","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,5,8]]},"article-number":"9"}}