{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T14:00:07Z","timestamp":1777557607107,"version":"3.51.4"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688274","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T15:31:00Z","timestamp":1643902260000},"page":"1147-1154","source":"Crossref","is-referenced-by-count":8,"title":["\u201cHow Robust R U?\u201d: Evaluating Task-Oriented Dialogue Systems on Spoken Conversations"],"prefix":"10.1109","author":[{"given":"Seokhwan","family":"Kim","sequence":"first","affiliation":[{"name":"Amazon Alexa AI,Sunnyvale,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI,Sunnyvale,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Jin","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI,Sunnyvale,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandros","family":"Papangelis","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI,Sunnyvale,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karthik","family":"Gopalakrishnan","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI,Sunnyvale,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Behnam","family":"Hedayatnia","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI,Sunnyvale,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dilek","family":"Hakkani-Tur","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI,Sunnyvale,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","author":"mehri","year":"2020","journal-title":"Dialoglue A natural language understanding benchmark for task-oriented dialogue"},{"key":"ref32","author":"devlin","year":"2019","journal-title":"BERT Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref31","first-page":"35","article-title":"Trippy: A triple copy strategy for value independent neural dialog state tracking","author":"heck","year":"0","journal-title":"Proceedings of the 21 th Annual Meeting of the Special Interest Group on Discourse and Dialogue"},{"key":"ref30","author":"gunasekara","year":"2020","journal-title":"Overview of the ninth dialog system technology challenge Dstc9"},{"key":"ref36","author":"bao","year":"2021","journal-title":"Plato-2 Towards building an open-domain chatbot via curriculum learning"},{"key":"ref35","author":"radford","year":"2019","journal-title":"Language Models are Unsupervised Multitask Learners"},{"key":"ref34","author":"he","year":"2021","journal-title":"Learning to select external knowledge with multi-scale negative sampling"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1583"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846295"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003825"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.347"},{"key":"ref14","first-page":"278","article-title":"Beyond domain apis: Task-oriented conversational modeling with unstructured knowledge access","author":"kim","year":"0","journal-title":"Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053213"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-591"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.nlp4convai-1.8"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4337"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078595"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6394"},{"key":"ref27","author":"baevski","year":"2020","journal-title":"wav2vec 2 0 A framework for self-supervised learning of speech representations"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1547"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2005.07.005"},{"key":"ref29","first-page":"187","article-title":"Kenlm: Faster and smaller language model queries","author":"heafield","year":"0","journal-title":"Proceedings of the Sixth Workshop on Statistical Machine Translation"},{"key":"ref5","article-title":"Improving spoken language understanding using word confusion networks","author":"tur","year":"0","journal-title":"Seventh International Conference on Spoken Language Processing"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-580"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424218"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-1042"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462030"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5526"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-2585-3_36"},{"key":"ref22","article-title":"Raddle: An evaluation benchmark and analysis platform for robust task-oriented dialog systems","author":"peng","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846311"},{"key":"ref24","article-title":"Multiwoz 2.1: Multi-domain dialogue state corrections and state tracking baselines","author":"eric","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1508"},{"key":"ref26","author":"eric","year":"2021","journal-title":"Beyond domain apis Task-oriented conversational modeling with unstructured knowledge access track in dstc9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.nlp4convai-1.13"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Cartagena, Colombia","start":{"date-parts":[[2021,12,13]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688274.pdf?arnumber=9688274","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T16:42:15Z","timestamp":1652719335000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688274\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688274","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}