{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:12:25Z","timestamp":1760026345873,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,3,11]],"date-time":"2024-03-11T00:00:00Z","timestamp":1710115200000},"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":[[2024,3,11]]},"DOI":"10.1145\/3610978.3640689","type":"proceedings-article","created":{"date-parts":[[2024,3,10]],"date-time":"2024-03-10T22:55:43Z","timestamp":1710111343000},"page":"593-597","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Name Pronunciation Extraction and Reuse in Human-Robot Conversations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2760-8318","authenticated-orcid":false,"given":"James","family":"Kennedy","sequence":"first","affiliation":[{"name":"Disney Research, Glendale, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0604-2466","authenticated-orcid":false,"given":"Naveen","family":"Kumar","sequence":"additional","affiliation":[{"name":"Disney Research, Glendale, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8418-3024","authenticated-orcid":false,"given":"Maike","family":"Paetzel-Pr\u00fcsmann","sequence":"additional","affiliation":[{"name":"Disney Research, Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,3,11]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-49186-4_31"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892285"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2003.07.003"},{"key":"e_1_3_2_2_4_1","volume-title":"Social robots for education: A review. Science robotics","author":"Belpaeme Tony","year":"2018","unstructured":"Tony Belpaeme, James Kennedy, Aditi Ramachandran, Brian Scassellati, and Fumihide Tanaka. 2018. Social robots for education: A review. Science robotics, Vol. 3, 21 (2018), eaat5954."},{"key":"e_1_3_2_2_5_1","volume-title":"The 2 sigma problem: The search for methods of group instruction as effective as one-to-one tutoring. Educational researcher","author":"Bloom Benjamin S","year":"1984","unstructured":"Benjamin S Bloom. 1984. The 2 sigma problem: The search for methods of group instruction as effective as one-to-one tutoring. Educational researcher, Vol. 13, 6 (1984), 4--16."},{"key":"e_1_3_2_2_6_1","volume-title":"Anne Loomis Thompson, and Eric Horvitz","author":"Bohus Dan","year":"2021","unstructured":"Dan Bohus, Sean Andrist, Ashley Feniello, Nick Saw, Mihai Jalobeanu, Patrick Sweeney, Anne Loomis Thompson, and Eric Horvitz. 2021. Platform for Situated Intelligence. arxiv: 2103.15975 [cs.AI]"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.76.6.893"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s43154-020-00009-2"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639513"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/DevLrn.2013.6652569"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2009.5354149"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477963"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10315-0"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2019.00054"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053893"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2750858.2807552"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2981314"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11257-020-09267-3"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793770"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1075\/li.30.1.03nad"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2015.2445105"},{"key":"e_1_3_2_2_23_1","volume-title":"Proceedings of the 10th international seminar on speech production, cologne. 391--394","author":"Schweitzer Antje","year":"2014","unstructured":"Antje Schweitzer and Natalie Lewandowski. 2014. Social factors in convergence of F1 and F2 in spontaneous speech. In Proceedings of the 10th international seminar on speech production, cologne. 391--394."},{"key":"e_1_3_2_2_24_1","volume-title":"FLERT: Document-Level Features for Named Entity Recognition. arxiv","author":"Schweter Stefan","year":"2020","unstructured":"Stefan Schweter and Alan Akbik. 2020. FLERT: Document-Level Features for Named Entity Recognition. arxiv: 2011.06993 [cs.CL]"},{"key":"e_1_3_2_2_25_1","volume-title":"Seq-2-Seq based Refinement of ASR Output for Spoken Name Capture. arXiv preprint arXiv:2203.15833","author":"Singla Karan","year":"2022","unstructured":"Karan Singla, Shahab Jalalvand, Yeon-Jun Kim, Ryan Price, Daniel Pressel, and Srinivas Bangalore. 2022. Seq-2-Seq based Refinement of ASR Output for Spoken Name Capture. arXiv preprint arXiv:2203.15833 (2022)."},{"key":"e_1_3_2_2_26_1","volume-title":"E2E Spoken Entity Extraction for Virtual Agents. CoRR","author":"Singla Karan","year":"2023","unstructured":"Karan Singla, Yeon-Jun Kim, Ryan Price, Shahab Jalalvand, and Srinivas Bangalore. 2023. E2E Spoken Entity Extraction for Virtual Agents. CoRR (2023)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1468-2958.1984.tb00043.x"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3439720"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-31372-2_4"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3319502.3374780"},{"key":"e_1_3_2_2_31_1","unstructured":"ROS Wiki. 2018. message_filters wiki.ros.org. https:\/\/wiki.ros.org\/message_filters#Time_Synchronizer. [Accessed 21--11--2023]."},{"key":"e_1_3_2_2_32_1","volume-title":"Simple and Effective Zero-shot Cross-lingual Phoneme Recognition. CoRR","author":"Xu Qiantong","year":"2021","unstructured":"Qiantong Xu, Alexei Baevski, and Michael Auli. 2021a. Simple and Effective Zero-shot Cross-lingual Phoneme Recognition. CoRR, Vol. abs\/2109.11680 (2021). showeprint[arXiv]2109.11680 https:\/\/arxiv.org\/abs\/2109.11680"},{"key":"e_1_3_2_2_33_1","volume-title":"Simple and effective zero-shot cross-lingual phoneme recognition. arXiv preprint arXiv:2109.11680","author":"Xu Qiantong","year":"2021","unstructured":"Qiantong Xu, Alexei Baevski, and Michael Auli. 2021b. Simple and effective zero-shot cross-lingual phoneme recognition. arXiv preprint arXiv:2109.11680 (2021)."},{"key":"e_1_3_2_2_34_1","volume-title":"https:\/\/huggingface.co\/facebook\/wav2vec2-lv-60-espeak-cv-ft. Accessed on","author":"Xu Qiantong","year":"2023","unstructured":"Qiantong Xu, Alexei Baevski, and Michael Auli. 2023. Wav2Vec 2.0 LV-60 ESpeak CV Fine-Tuned Model. https:\/\/huggingface.co\/facebook\/wav2vec2-lv-60-espeak-cv-ft. Accessed on: 2023."},{"key":"e_1_3_2_2_35_1","volume-title":"End-to-end named entity recognition from english speech. arXiv preprint arXiv:2005.11184","author":"Yadav Hemant","year":"2020","unstructured":"Hemant Yadav, Sreyan Ghosh, Yi Yu, and Rajiv Ratn Shah. 2020. End-to-end named entity recognition from english speech. arXiv preprint arXiv:2005.11184 (2020)."},{"key":"e_1_3_2_2_36_1","volume-title":"A survey on recent advances in named entity recognition from deep learning models. arXiv preprint arXiv:1910.11470","author":"Yadav Vikas","year":"2019","unstructured":"Vikas Yadav and Steven Bethard. 2019. A survey on recent advances in named entity recognition from deep learning models. arXiv preprint arXiv:1910.11470 (2019)."}],"event":{"name":"HRI '24: ACM\/IEEE International Conference on Human-Robot Interaction","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction"],"location":"Boulder CO USA","acronym":"HRI '24"},"container-title":["Companion of the 2024 ACM\/IEEE International Conference on Human-Robot Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3610978.3640689","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3610978.3640689","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T01:26:12Z","timestamp":1755825972000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3610978.3640689"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,11]]},"references-count":36,"alternative-id":["10.1145\/3610978.3640689","10.1145\/3610978"],"URL":"https:\/\/doi.org\/10.1145\/3610978.3640689","relation":{},"subject":[],"published":{"date-parts":[[2024,3,11]]},"assertion":[{"value":"2024-03-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}