{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:21:48Z","timestamp":1776885708325,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T00:00:00Z","timestamp":1710288000000},"content-version":"vor","delay-in-days":366,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2226165"],"award-info":[{"award-number":["2226165"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,3,13]]},"DOI":"10.1145\/3568294.3580053","type":"proceedings-article","created":{"date-parts":[[2023,3,8]],"date-time":"2023-03-08T18:51:31Z","timestamp":1678301491000},"page":"112-116","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Towards Robot Learning from Spoken Language"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7663-2790","authenticated-orcid":false,"given":"Krishna","family":"Kodur","sequence":"first","affiliation":[{"name":"Santa Clara University, Santa Clara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1745-8523","authenticated-orcid":false,"given":"Manizheh","family":"Zand","sequence":"additional","affiliation":[{"name":"Santa Clara University, Santa Clara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0968-2477","authenticated-orcid":false,"given":"Maria","family":"Kyrarini","sequence":"additional","affiliation":[{"name":"Santa Clara University, Santa Clara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,3,13]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"CDC \"Disability impacts all of us \" 2022. [Online]. Available: https:\/\/www.cdc.gov\/ncbddd\/disabilityandhealth\/infographic-disability- impacts-all.html#: :text=61%20million%20adults%20in%20the have%20some% 20type%20of%20disability"},{"key":"e_1_3_2_2_2_1","unstructured":"WHO \"Health and ageing \" 2022. [Online]. Available: https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/ageing-and-health#: :text=By%202030%2C%201%20in%206 will%20double%20(2.1%20billion)"},{"key":"e_1_3_2_2_3_1","volume-title":"Functional assessment and performance evaluation for assistive robotic manipulators: Literature review,\" The journal of spinal cord medicine","author":"Chung C.-S.","unstructured":"C.-S. Chung, H. Wang, and R. A. Cooper, \"Functional assessment and performance evaluation for assistive robotic manipulators: Literature review,\" The journal of spinal cord medicine, vol. 36, no. 4, pp. 273--289, 2013."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574711000051"},{"key":"e_1_3_2_2_5_1","first-page":"1139","volume-title":"IEEE","author":"Kyrarini M.","year":"2019","unstructured":"M. Kyrarini, Q. Zheng, M. A. Haseeb, and A. Gr\u00e4ser, \"Robot learning of assistive manipulation tasks by demonstration via head gesture-based interface,\" in 2019 IEEE 16th International Conference on Rehabilitation Robotics (ICORR). IEEE, 2019, pp. 1139--1146."},{"key":"e_1_3_2_2_6_1","first-page":"210","volume-title":"IEEE","author":"Goldau F. F.","year":"2019","unstructured":"F. F. Goldau, T. K. Shastha, M. Kyrarini, and A. Gr\u00e4ser, \"Autonomous multisensory robotic assistant for a drinking task,\" in 2019 IEEE 16th International Conference on Rehabilitation Robotics (ICORR). IEEE, 2019, pp. 210--216."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.3390\/technologies10010030"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-019-00306-x"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101255"},{"key":"e_1_3_2_2_10_1","volume-title":"Concept2robot: Learn- ing manipulation concepts from instructions and human demonstrations,\" in Proceedings of Robotics: Science and Systems (RSS)","author":"Shao L.","year":"2020","unstructured":"L. Shao, T. Migimatsu, Q. Zhang, K. Yang, and J. Bohg, \"Concept2robot: Learn- ing manipulation concepts from instructions and human demonstrations,\" in Proceedings of Robotics: Science and Systems (RSS), 2020."},{"key":"e_1_3_2_2_11_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin J.","year":"2018","unstructured":"J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, \"Bert: Pre-training of deep bidirectional transformers for language understanding,\" 2018. [Online]. Available: https:\/\/arxiv.org\/abs\/1810.04805"},{"key":"e_1_3_2_2_12_1","volume-title":"Deep residual learning for image recognition","author":"He K.","year":"2015","unstructured":"K. He, X. Zhang, S. Ren, and J. Sun, \"Deep residual learning for image recognition,\" 2015. [Online]. Available: https:\/\/arxiv.org\/abs\/1512.03385"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2021.626380"},{"key":"e_1_3_2_2_15_1","volume-title":"You only look once: Unified, real-time object detection","author":"Redmon J.","year":"2015","unstructured":"J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, \"You only look once: Unified, real-time object detection,\" 2015. [Online]. Available: https: \/\/arxiv.org\/abs\/1506.02640"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","unstructured":"V. V. Unhelkar S. Li and J. A. Shah \"Decision-making for bidirectional communication in sequential human-robot collaborative tasks \" Proceedings of the 2020 ACM\/IEEE International Conference on Human-Robot Interaction. [Online]. Available: https:\/\/doi.org\/10.1145\/3319502.3374779","DOI":"10.1145\/3319502.3374779"},{"key":"e_1_3_2_2_17_1","first-page":"216","article-title":"Controlling industrial robots with high-level verbal commands","volume":"13086","author":"Choi D.","year":"2021","unstructured":"D. Choi, W. Shi, Y. S. Liang, K. H. Yeo, and J. J. Kim, \"Controlling industrial robots with high-level verbal commands,\" Lecture Notes in Computer Science including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics, vol. 13086 LNAI, pp. 216--226, 2021. [Online]. Available: https:\/\/link.springer.com\/chapter\/10.1007\/978-3-030-90525-5_19","journal-title":"Lecture Notes in Computer Science including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics"},{"key":"e_1_3_2_2_18_1","first-page":"1","article-title":"Tod4ir: A humanised task- oriented dialogue system for industrial robots","author":"Li C.","year":"2022","unstructured":"C. Li, X. Zhang, D. Chrysostomou, and H. Yang, \"Tod4ir: A humanised task- oriented dialogue system for industrial robots,\" IEEE Access, pp. 1--1, 8 2022.","journal-title":"IEEE Access"},{"key":"e_1_3_2_2_19_1","volume-title":"Language models are unsupervised multitask learners","author":"Radford A.","year":"2018","unstructured":"A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, and I. Sutskever, \"Language models are unsupervised multitask learners,\" 2018. [Online]. Available: https: \/\/d4mucfpksywv.cloudfront.net\/better-language-models\/language-models.pdf"},{"key":"e_1_3_2_2_20_1","volume-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"Ahn M.","year":"2022","unstructured":"M. Ahn, A. Brohan, N. Brown, Y. Chebotar, O. Cortes, B. David, C. Finn, C. Fu, K. Gopalakrishnan, K. Hausman, A. Herzog, D. Ho, J. Hsu, J. Ibarz, B. Ichter, A. Irpan, E. Jang, R. J. Ruano, K. Jeffrey, S. Jesmonth, N. J. Joshi, R. Julian, D. Kalashnikov, Y. Kuang, K.-H. Lee, S. Levine, Y. Lu, L. Luu, C. Parada, P. Pastor, J. Quiambao, K. Rao, J. Rettinghouse, D. Reyes, P. Sermanet, N. Sievers, C. Tan, A. Toshev, V. Vanhoucke, F. Xia, T. Xiao, P. Xu, S. Xu, M. Yan, and A. Zeng, \"Do as i can, not as i say: Grounding language in robotic affordances,\" 2022. [Online]. Available: https:\/\/arxiv.org\/abs\/2204.01691"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3463516"},{"key":"e_1_3_2_2_22_1","unstructured":"\"Vosk models.\" [Online]. Available: https:\/\/alphacephei.com\/vosk\/models"},{"key":"e_1_3_2_2_23_1","unstructured":"English Study Here \"Food adjectives -- list of food adjectives \" 2018. [Online]. Available: https:\/\/englishstudyhere.com\/grammar\/adjectives\/food-adjectives-list-of-food-adjectives\/"},{"key":"e_1_3_2_2_24_1","unstructured":"F. Network \"Recipes a to z \" 2022. [Online]. Available: https:\/\/www.foodnetwork. com\/recipes\/recipes-a-z\/123"},{"key":"e_1_3_2_2_25_1","unstructured":"O. S. University \"Ingredients list \" 2021. [Online]. Available: https:\/\/www. foodhero.org\/ingredients"},{"key":"e_1_3_2_2_26_1","volume-title":"Tweetqa: A social media focused question answering dataset","author":"Xiong W.","year":"2019","unstructured":"W. Xiong, J. Wu, H. Wang, V. Kulkarni, M. Yu, S. Chang, X. Guo, and W. Y. Wang, \"Tweetqa: A social media focused question answering dataset,\" 2019. [Online]. Available: https:\/\/arxiv.org\/abs\/1907.06292"},{"key":"e_1_3_2_2_27_1","unstructured":"\"Distilgpt2.\" [Online]. Available: https:\/\/huggingface.co\/distilgpt2"},{"key":"e_1_3_2_2_28_1","first-page":"2398","volume-title":"IEEE","author":"Kyrarini M.","year":"2017","unstructured":"M. Kyrarini, S. Naeem, X. Wang, and A. Gr\u00e4ser, \"Skill robot library: Intelligent path planning framework for object manipulation,\" in 2017 25th European Signal Processing Conference (EUSIPCO). IEEE, 2017, pp. 2398--2402."}],"event":{"name":"HRI '23: ACM\/IEEE International Conference on Human-Robot Interaction","location":"Stockholm Sweden","acronym":"HRI '23","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Companion of the 2023 ACM\/IEEE International Conference on Human-Robot Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3568294.3580053","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3568294.3580053","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3568294.3580053","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T22:57:40Z","timestamp":1755817060000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3568294.3580053"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,13]]},"references-count":28,"alternative-id":["10.1145\/3568294.3580053","10.1145\/3568294"],"URL":"https:\/\/doi.org\/10.1145\/3568294.3580053","relation":{},"subject":[],"published":{"date-parts":[[2023,3,13]]},"assertion":[{"value":"2023-03-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}