{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T18:09:37Z","timestamp":1772302177687,"version":"3.50.1"},"reference-count":23,"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\/icassp49357.2023.10095629","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":5,"title":["Toward A Multimodal Approach for Disfluency Detection and Categorization"],"prefix":"10.1109","author":[{"given":"Amrit","family":"Romana","sequence":"first","affiliation":[{"name":"University of Michigan,Computer Science and Engineering,Ann Arbor,Michigan,USA"}]},{"given":"Kazuhito","family":"Koishida","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,Redmond,Washington,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1749-818X.2008.00068.x"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-360"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-114"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1694"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.04.146"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413520"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1490"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1336"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3134"},{"key":"ref11","article-title":"Identification of primary and collateral tracks in stuttered speech","volume-title":"Proc. Conference on Language Resources and Evaluation","author":"Riad"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-351"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10971"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10908"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfludis.2018.03.002"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfludis.2006.02.002"},{"key":"ref18","article-title":"The kaldi speech recognition toolkit","volume-title":"IEEE workshop on automatic speech recognition and understanding","author":"Povey"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"ref20","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref23","article-title":"Dawn of the transformer era in speech emotion recognition: closing the valence gap","author":"Wagner","year":"2022","journal-title":"arXiv:2203.07378"}],"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\/10095629.pdf?arnumber=10095629","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T08:13:59Z","timestamp":1710404039000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095629\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095629","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}