{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T21:25:13Z","timestamp":1776115513401,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,19]],"date-time":"2023-04-19T00:00:00Z","timestamp":1681862400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,19]]},"DOI":"10.1145\/3544549.3585609","type":"proceedings-article","created":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T07:31:00Z","timestamp":1681975860000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Modeling and Improving Text Stability in Live Captions"],"prefix":"10.1145","author":[{"given":"Xingyu \"Bruce\"","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8527-1744","authenticated-orcid":false,"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8527-1744","authenticated-orcid":false,"given":"Leonardo","family":"Ferrer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8527-1744","authenticated-orcid":false,"given":"Susan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8527-1744","authenticated-orcid":false,"given":"Vikas","family":"Bahirwani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8527-1744","authenticated-orcid":false,"given":"Boris","family":"Smus","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8527-1744","authenticated-orcid":false,"given":"Alex","family":"Olwal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2471-9776","authenticated-orcid":false,"given":"Ruofei","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,4,19]]},"reference":[{"key":"e_1_3_3_3_1_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1750"},{"key":"e_1_3_3_3_2_1","doi-asserted-by":"crossref","unstructured":"Jacob Aron. 2011. How innovative is Apple\u2019s new voice assistant Siri?","DOI":"10.1016\/S0262-4079(11)62647-X"},{"key":"e_1_3_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132525.3132541"},{"key":"e_1_3_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308561.3353772"},{"key":"e_1_3_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379155.3391313"},{"key":"e_1_3_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501920"},{"key":"e_1_3_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874013"},{"key":"e_1_3_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3234695.3236362"},{"key":"e_1_3_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3470651"},{"key":"e_1_3_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308561.3353781"},{"key":"e_1_3_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2982142.2982164"},{"key":"e_1_3_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2509315.2509331"},{"key":"e_1_3_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/rrq.59"},{"key":"e_1_3_3_3_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025772"},{"key":"e_1_3_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2384916.2384930"},{"key":"e_1_3_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2982142.2982164"},{"key":"e_1_3_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE.2013.6486929"},{"key":"e_1_3_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-352"},{"key":"e_1_3_3_3_19_1","doi-asserted-by":"publisher","unstructured":"Zehan Li Haoran Miao Keqi Deng Gaofeng Cheng Sanli Tian Ta Li and Yonghong Yan. 2022. Improving Streaming End-to-End ASR on Transformer-Based Causal Models With Encoder States Revision Strategies. https:\/\/doi.org\/10.48550\/ARXIV.2207.02495","DOI":"10.48550\/ARXIV.2207.02495"},{"key":"e_1_3_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581566"},{"key":"e_1_3_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3526113.3545703"},{"key":"e_1_3_3_3_22_1","volume-title":"Annual Meeting of the Association for Computational Linguistics. Association for Computing Machinery","author":"Ma Mingbo","year":"2018","unstructured":"Mingbo Ma, Liang Huang, Hao Xiong, Renjie Zheng, Kaibo Liu, Baigong Zheng, Chuanqiang Zhang, Zhongjun He, Hairong Liu, Xing Li, Hua Wu, and Haifeng Wang. 2018. STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework. In Annual Meeting of the Association for Computational Linguistics. Association for Computing Machinery, New York, NY, USA, 10."},{"key":"e_1_3_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/11853565_10"},{"key":"e_1_3_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2331714.2331720"},{"key":"e_1_3_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10209-008-0136-x"},{"key":"e_1_3_3_3_26_1","doi-asserted-by":"publisher","unstructured":"Thai\u00a0Son Nguyen Jan Niehues Eunah Cho Thanh-Le Ha Kevin Kilgour Markus Muller Matthias Sperber Sebastian Stueker and Alex Waibel. 2020. Low Latency ASR for Simultaneous Speech Translation. https:\/\/doi.org\/10.48550\/ARXIV.2003.09891","DOI":"10.48550\/ARXIV.2003.09891"},{"key":"e_1_3_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415817"},{"key":"e_1_3_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-5107"},{"key":"e_1_3_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290607.3312921"},{"key":"e_1_3_3_3_30_1","volume-title":"Sentence-Bert: Sentence Embeddings Using Siamese Bert-Networks. ArXiv Preprint ArXiv:1908.10084 1","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-Bert: Sentence Embeddings Using Siamese Bert-Networks. ArXiv Preprint ArXiv:1908.10084 1 (2019), 10. https:\/\/arxiv.org\/pdf\/1908.10084"},{"key":"e_1_3_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.1057\/978113755289_3"},{"key":"e_1_3_3_3_32_1","volume-title":"Analyzing the Quality and Stability of a Streaming End-to-End On-Device Speech Recognizer. CoRR abs\/2006.01416","author":"Shangguan Yuan","year":"2020","unstructured":"Yuan Shangguan, Kate Knister, Yanzhang He, Ian McGraw, and Fran\u00e7oise Beaufays. 2020. Analyzing the Quality and Stability of a Streaming End-to-End On-Device Speech Recognizer. CoRR abs\/2006.01416 (2020), 10. arXiv:2006.01416https:\/\/arxiv.org\/abs\/2006.01416"},{"key":"e_1_3_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2700648.2809857"},{"key":"e_1_3_3_3_34_1","volume-title":"CHI 2022 Town Hall. ACM SIGCHI. https:\/\/www.youtube.com\/watch?v=dDPPNyUDmco","author":"ACM SIGCHI.","unstructured":"ACM SIGCHI. 2. CHI 2022 Town Hall. ACM SIGCHI. https:\/\/www.youtube.com\/watch?v=dDPPNyUDmco"},{"key":"e_1_3_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.1177\/0022466907313453"},{"key":"e_1_3_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.1177\/0022466907313453"},{"key":"e_1_3_3_3_37_1","volume-title":"Interspeech.","author":"Swarup Prakhar","unstructured":"Prakhar Swarup, Roland Maas, Sri Garimella, Sri\u00a0Harish Mallidi, and Bj\u00f6rn Hoffmeister. 2019. Improving ASR Confidence Scores for Alexa Using Acoustic and Hypothesis Embeddings.. In Interspeech. Interspeech, New York, NY, USA, 2175\u20132179."},{"key":"e_1_3_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.512550"},{"key":"e_1_3_3_3_39_1","volume-title":"Dynamic Masking for Improved Stability in Online Spoken Language Translation. In Conference of the Association for Machine Translation in the Americas. Association for Computing Machinery","author":"Yao Yuekun","year":"2020","unstructured":"Yuekun Yao and Barry Haddow. 2020. Dynamic Masking for Improved Stability in Online Spoken Language Translation. In Conference of the Association for Machine Translation in the Americas. Association for Computing Machinery, New York, NY, USA, 10."}],"event":{"name":"CHI '23: CHI Conference on Human Factors in Computing Systems","location":"Hamburg Germany","acronym":"CHI '23","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3544549.3585609","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3544549.3585609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:33Z","timestamp":1750178793000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3544549.3585609"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,19]]},"references-count":39,"alternative-id":["10.1145\/3544549.3585609","10.1145\/3544549"],"URL":"https:\/\/doi.org\/10.1145\/3544549.3585609","relation":{},"subject":[],"published":{"date-parts":[[2023,4,19]]},"assertion":[{"value":"2023-04-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}