{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T14:53:42Z","timestamp":1784904822070,"version":"3.55.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10094620","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":7,"title":["Streaming Joint Speech Recognition and Disfluency Detection"],"prefix":"10.1109","author":[{"given":"Hayato","family":"Futami","sequence":"first","affiliation":[{"name":"Sony Group Corporation,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emiru","family":"Tsunoo","sequence":"additional","affiliation":[{"name":"Sony Group Corporation,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kentaro","family":"Shibata","sequence":"additional","affiliation":[{"name":"Sony Group Corporation,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yosuke","family":"Kashiwagi","sequence":"additional","affiliation":[{"name":"Sony Group Corporation,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takao","family":"Okuda","sequence":"additional","affiliation":[{"name":"Sony Group Corporation,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siddhant","family":"Arora","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Preliminaries to a theory of speech disfluencies","volume-title":"Tech. Rep.","author":"Shriberg","year":"1994"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639661"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.293"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10161"},{"key":"ref5","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"NAACL","author":"Devlin"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.346"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-351"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.286"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.60"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1008"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.149"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747674"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746067"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003749"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414560"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383517"},{"key":"ref18","article-title":"Monotonic chunkwise attention","volume-title":"ICLR","author":"Chiu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683510"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1296"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1490"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1336"},{"key":"ref23","first-page":"3529","article-title":"Semi-supervised disfluency detection","author":"Wang","year":"2018","journal-title":"COLING"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016351"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-400"},{"key":"ref26","first-page":"6214","article-title":"An end-to-end approach to joint social signal detection and automatic speech recognition","volume-title":"ICASSP","author":"Inaguma"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.186"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-281"},{"key":"ref29","first-page":"619","article-title":"Phonetic consequences of speech disfluency","author":"Shriberg","year":"1999","journal-title":"ICPhS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref31","article-title":"Corpus of Spontaneous Japanese : its design and evaluation","author":"Maekawa","year":"2003","journal-title":"SSPR"},{"key":"ref32","article-title":"Treebank-3 LDC99T42","author":"Marcus","year":"1999","journal-title":"Linguistic Data Consortium"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133217"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60276-5_27"},{"key":"ref37","article-title":"The Fisher Corpus: a resource for the next generations of speech- to-text","volume-title":"LREC","author":"Cieri"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10094620.pdf?arnumber=10094620","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:50:55Z","timestamp":1705020655000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094620\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094620","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}