{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T10:37:56Z","timestamp":1756636676715,"version":"3.37.3"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004663","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":[[2019,9]]},"DOI":"10.1109\/taslp.2019.2913499","type":"journal-article","created":{"date-parts":[[2019,4,27]],"date-time":"2019-04-27T06:13:43Z","timestamp":1556345623000},"page":"1469-1480","source":"Crossref","is-referenced-by-count":6,"title":["Machine Comprehension of Spoken Content: TOEFL Listening Test and Spoken SQuAD"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1933-5703","authenticated-orcid":false,"given":"Chia-Hsuan","family":"Lee","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9654-5747","authenticated-orcid":false,"given":"Hung-yi","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Szu-Lin","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Chi-Liang","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8139-1119","authenticated-orcid":false,"given":"Wei","family":"Fang","sequence":"additional","affiliation":[]},{"given":"Juei-Yang","family":"Hsu","sequence":"additional","affiliation":[]},{"given":"Bo-Hsiang","family":"Tseng","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"451","article-title":"Ask, attend and answer: Exploring question-guided spatial attention for visual question answering","author":"xu","year":"0","journal-title":"Proc Comput Vision Pattern Recognit"},{"key":"ref38","article-title":"ABC-CNN: An attention based convolutional neural network for visual question answering","author":"chen","year":"0","journal-title":"Proc Comput Vision Pattern Recognit"},{"key":"ref33","article-title":"QANet: Combining local convolution with global self-attention for reading comprehension","author":"yu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"article-title":"FusionNet: Fusing via fully-aware attention with application to machine comprehension","year":"2017","author":"huang","key":"ref32"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/570"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.cviu.2017.05.001","article-title":"Visual question answering: A survey of methods and datasets","volume":"163","author":"wu","year":"2017","journal-title":"Comput Vision Image Understand"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1055"},{"key":"ref60","first-page":"1899","article-title":"Compositional morphology for word representations and language modelling","author":"botha","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref61","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1007\/978-3-662-44848-9_9","article-title":"Knowledge-powered deep learning for word embedding","author":"bian","year":"2014","journal-title":"Proc Eur Conf Mach Learn Knowl Discovery Databases"},{"key":"ref28","article-title":"Dynamic coattention networks for question answering","author":"xiong","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-363"},{"key":"ref27","article-title":"Towards neural network-based reasoning","author":"peng","year":"2015","journal-title":"CoRR"},{"article-title":"Bidirectional attention flow for machine comprehension","year":"2016","author":"seo","key":"ref29"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846270"},{"key":"ref1","article-title":"Towards machine learning comprehension of spoken content: Initial TOEFL listening comprehension test by machine","author":"tseng","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref20","article-title":"Large-scale simple question answering with memory networks","author":"bordes","year":"2015","journal-title":"CoRR"},{"key":"ref22","first-page":"2397","article-title":"Dynamic memory networks for visual and textual question answering","author":"xiong","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","first-page":"1378","article-title":"Ask me anything: Dynamic memory networks for natural language processing","author":"kumar","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","article-title":"Where to look: Focus regions for visual question answering","author":"shih","year":"2015","journal-title":"CoRR"},{"key":"ref23","first-page":"1693","article-title":"Teaching machines to read and comprehend","author":"hermann","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","article-title":"Weakly supervised memory networks","author":"sukhbaatar","year":"2015","journal-title":"CoRR"},{"key":"ref25","article-title":"Memory networks","author":"weston","year":"2014","journal-title":"CoRR"},{"key":"ref50","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","author":"socher","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref59","first-page":"104","article-title":"Better word representations with recursive neural networks for morphology","author":"luong","year":"0","journal-title":"Proc Conf Computational Natural Language Learning"},{"key":"ref58","first-page":"2741","article-title":"Character-aware neural language models","author":"kim","year":"0","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref57","first-page":"649","article-title":"Character-level convolutional networks for text classification","author":"zhang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1171"},{"key":"ref55","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref54","first-page":"26","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"Neural Netw Mach Learning"},{"key":"ref53","first-page":"635","article-title":"Maintaining stream statistics over sliding windows: (Extended abstract)","author":"datar","year":"0","journal-title":"Proc 13th Annu ACM-SIAM Symp Discrete Algorithms"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-5010"},{"key":"ref10","first-page":"314","article-title":"Overview of QAST 2008","author":"turmo","year":"2008","journal-title":"Proc Workshop Cross-Lang Eval Forum Eur Lang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1038-2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2328967.2328972"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1067"},{"key":"ref13","first-page":"854","article-title":"A factoid question answering system using answer pattern matching","author":"er","year":"0","journal-title":"Proc 6th Int Joint Conf Natural Lang Process"},{"key":"ref14","first-page":"633","author":"iyyer","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623677"},{"key":"ref16","article-title":"Towards AI-complete question answering: A set of prerequisite toy tasks","author":"weston","year":"2015","journal-title":"CoRR"},{"key":"ref17","first-page":"193","article-title":"MCTest: A challenge dataset for the open-domain machine comprehension of text","author":"richardson","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"article-title":"MS MARCO: A human generated machine reading comprehension dataset","year":"2016","author":"nguyen","key":"ref19"},{"article-title":"Factoid question answering for spoken documents","year":"2012","author":"umbert","key":"ref4"},{"article-title":"Spoken question answering.","year":"0","author":"umbert","key":"ref3"},{"key":"ref6","first-page":"949","article-title":"ODSQA: Open-domain spoken question answering dataset","author":"lee","year":"0","journal-title":"Proc IEEE Spoken Lang Technol Workshop"},{"key":"ref5","first-page":"3459","article-title":"Spoken SQuAD: A study of mitigating the impact of speech recognition errors on listening comprehension","author":"li","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref8","first-page":"263","article-title":"Spoken question answering using tree-structured conditional random fields and two-layer random walk","author":"shiang","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1150"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683377"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1086"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"ref45","article-title":"Leveraging video descriptions to learn video question answering","author":"zeng","year":"0","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"article-title":"Sphinx-4: A flexible open source framework for speech recognition","year":"2004","author":"walker","key":"ref48"},{"key":"ref47","article-title":"A compare-aggregate model for matching text sequences","author":"wang","year":"2016","journal-title":"CoRR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1033-7"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"article-title":"MarioQA: Answering questions by watching gameplay videos","year":"2016","author":"mun","key":"ref44"},{"key":"ref43","first-page":"42","article-title":"Joint video and text parsing for understanding events and answering queries","author":"tu","year":"0","journal-title":"Proc Multimedia"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8736368\/08700217.pdf?arnumber=8700217","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:54:27Z","timestamp":1657745667000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8700217\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":63,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2913499","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2019,9]]}}}