{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T19:39:33Z","timestamp":1772825973008,"version":"3.50.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T00:00:00Z","timestamp":1748044800000},"content-version":"vor","delay-in-days":23,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Intel Serv Robotics"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s11370-025-00604-2","type":"journal-article","created":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T04:00:48Z","timestamp":1748059248000},"page":"389-401","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Multi-modal, multi-step human\u2013robot interaction method for natural interaction of service robots"],"prefix":"10.1007","volume":"18","author":[{"given":"Jargalbaatar","family":"Yura","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bat-Erdene","family":"Byambasuren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0477-3847","authenticated-orcid":false,"given":"Donghan","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,24]]},"reference":[{"issue":"5","key":"604_CR1","doi-asserted-by":"publisher","first-page":"1580","DOI":"10.1080\/14484846.2021.2023266","volume":"21","author":"D Bose","year":"2023","unstructured":"Bose D, Mohan K, CS M, Yadav M, Saini DK (2023) Review of autonomous campus and tour guiding robots with navigation techniques. Aust J Mech Eng 21(5):1580\u20131590","journal-title":"Aust J Mech Eng"},{"key":"604_CR2","doi-asserted-by":"publisher","first-page":"102600","DOI":"10.1016\/j.trd.2020.102600","volume":"89","author":"A Pani","year":"2020","unstructured":"Pani A, Mishra S, Golias M, Figliozzi M (2020) Evaluating public acceptance of autonomous delivery robots during covid-19 pandemic. Transp Res Part D: Transp Environ 89:102600","journal-title":"Transp Res Part D: Transp Environ"},{"key":"604_CR3","doi-asserted-by":"crossref","unstructured":"Xue R, Du Z, Yan Z, Ren B (2018) A design and evaluation of hand-held mechatronic laparoscopic surgical robot. In: 2018 International conference on control and robots (ICCR), pp.\u00a019\u201324, IEEE","DOI":"10.1109\/ICCR.2018.8534497"},{"key":"604_CR4","first-page":"336","volume":"2007","author":"M Nishimori","year":"2007","unstructured":"Nishimori M, Saitoh T, Konishi R (2007) Voice controlled intelligent wheelchair. SICE Ann Conf 2007:336\u2013340","journal-title":"SICE Ann Conf"},{"key":"604_CR5","unstructured":"Kondo Y (2013) Construction of reconfigurable motion database for real-time human-robot interaction. PhD thesis, Nara Institute of Science and Technology"},{"issue":"4","key":"604_CR6","first-page":"8269","volume":"3","author":"I Khan","year":"2013","unstructured":"Khan I, Abdullah H, Zainal MSB (2013) Efficient eyes and mouth detection algorithm using combination of Viola Jones and skin color pixel detection. Int J Eng 3(4):8269","journal-title":"Int J Eng"},{"issue":"6","key":"604_CR7","first-page":"1","volume":"7","author":"A El-Komy","year":"2022","unstructured":"El-Komy A, Shahin OR, Abd El-Aziz RM, Taloba AI (2022) Integration of computer vision and natural language processing in multimedia robotics application. Inf Sci 7(6):1","journal-title":"Inf Sci"},{"key":"604_CR8","doi-asserted-by":"publisher","first-page":"40979","DOI":"10.1109\/ACCESS.2022.3161440","volume":"10","author":"B Joksimoski","year":"2022","unstructured":"Joksimoski B, Zdravevski E, Lameski P, Pires IM, Melero FJ, Martinez TP, Garcia NM, Mihajlov M, Chorbev I, Trajkovik V (2022) Technological solutions for sign language recognition: a scoping review of research trends, challenges, and opportunities. IEEE Access 10:40979\u201340998","journal-title":"IEEE Access"},{"issue":"06","key":"604_CR9","doi-asserted-by":"publisher","first-page":"873","DOI":"10.1109\/TPAMI.2005.112","volume":"27","author":"SC Ong","year":"2005","unstructured":"Ong SC, Ranganath S (2005) Automatic sign language analysis: a survey and the future beyond lexical meaning. IEEE Trans Pattern Anal Machine Intell 27(06):873\u2013891","journal-title":"IEEE Trans Pattern Anal Machine Intell"},{"key":"604_CR10","doi-asserted-by":"crossref","unstructured":"Salim S, Jamil MMA, Ambar R, Wahab MHA (2022) A review on hand gesture and sign language techniques for hearing impaired person, Machine Learning Techniques for Smart City Applications: Trends and Solutions, pp.\u00a035\u201344","DOI":"10.1007\/978-3-031-08859-9_4"},{"key":"604_CR11","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1016\/j.engappai.2016.02.018","volume":"52","author":"J-B Kim","year":"2016","unstructured":"Kim J-B, Park J-S (2016) Multistage data selection-based unsupervised speaker adaptation for personalized speech emotion recognition. Eng Appl Artif Intell 52:126\u2013134","journal-title":"Eng Appl Artif Intell"},{"key":"604_CR12","doi-asserted-by":"crossref","unstructured":"Sharifuddin MSI, Nordin S, Ali AM (2019) Voice control intelligent wheelchair movement using cnns. In: 2019 1st International conference on artificial intelligence and data sciences (AiDAS), pp.\u00a040\u201343, IEEE","DOI":"10.1109\/AiDAS47888.2019.8970865"},{"key":"604_CR13","doi-asserted-by":"publisher","first-page":"3517995","DOI":"10.1155\/2022\/3517995","volume":"2022","author":"D Yang","year":"2022","unstructured":"Yang D et al (2022) Design of service robot based on user emotion recognition and environmental monitoring. J Environ Public Health 2022:3517995","journal-title":"J Environ Public Health"},{"key":"604_CR14","doi-asserted-by":"crossref","unstructured":"Tao R, Pan Z, Das RK, Qian X, Shou MZ, Li H (2021) Is someone speaking? exploring long-term temporal features for audio-visual active speaker detection. In: Proceedings of the 29th ACM international conference on multimedia, pp.\u00a03927\u20133935","DOI":"10.1145\/3474085.3475587"},{"key":"604_CR15","doi-asserted-by":"crossref","unstructured":"Avutu SR, Bhatia D, Reddy BV (2017) Voice control module for low cost local-map navigation based intelligent wheelchair. In: 2017 IEEE 7th international advance computing conference (IACC), pp.\u00a0609\u2013613, IEEE","DOI":"10.1109\/IACC.2017.0129"},{"key":"604_CR16","doi-asserted-by":"crossref","unstructured":"Khaewratana W, Veinott ES, Ramkumar SM (2020) Development of a generalized voice-controlled human-robot interface: one automatic speech recognition system for all robots, In: 2020 3rd International conference on control and robots (ICCR), pp.\u00a038\u201342","DOI":"10.1109\/ICCR51572.2020.9344123"},{"issue":"4","key":"604_CR17","doi-asserted-by":"publisher","first-page":"988","DOI":"10.1109\/TRO.2016.2588880","volume":"32","author":"P Liu","year":"2016","unstructured":"Liu P, Glas DF, Kanda T, Ishiguro H (2016) Data-driven hri: learning social behaviors by example from human\u2013human interaction. IEEE Trans Rob 32(4):988\u20131008","journal-title":"IEEE Trans Rob"},{"issue":"13","key":"604_CR18","doi-asserted-by":"publisher","first-page":"5798","DOI":"10.3390\/s23135798","volume":"23","author":"SK Paul","year":"2023","unstructured":"Paul SK, Nicolescu M, Nicolescu M (2023) Enhancing human\u2013robot collaboration through a multi-module interaction framework with sensor fusion: object recognition, verbal communication, user of interest detection, gesture and gaze recognition. Sensors 23(13):5798","journal-title":"Sensors"},{"key":"604_CR19","doi-asserted-by":"crossref","unstructured":"Mocan B, Fulea M, Brad S (2016) Designing a multimodal human-robot interaction interface for an industrial robot,\u201d in Advances in Robot Design and Intelligent Control: Proceedings of the 24th International Conference on Robotics in Alpe-Adria-Danube Region (RAAD), pp.\u00a0255\u2013263, Springer","DOI":"10.1007\/978-3-319-21290-6_26"},{"key":"604_CR20","unstructured":"Karbasi A, Sugiyama A (2007) A new doa estimation method using a circular microphone array. In: 2007 15th European signal processing conference, pp.\u00a0778\u2013782, IEEE"},{"key":"604_CR21","doi-asserted-by":"crossref","unstructured":"Valin J-M, Michaud F, Rouat J, Letourneau D (2003) Robust sound source localization using a microphone array on a mobile robot. In Proceedings 2003 IEEE\/RSJ international conference on intelligent robots and systems (IROS 2003) (Cat. No.03CH37453), 2, 1228\u20131233","DOI":"10.1109\/IROS.2003.1248813"},{"key":"604_CR22","unstructured":"Griffin A, Pavlidi D, Puigt M, Mouchtaris A (2012) Real-time multiple speaker doa estimation in a circular microphone array based on matching pursuit. In: 2012 Proceedings of the 20th European signal processing conference (EUSIPCO), pp.\u00a02303\u20132307, IEEE"},{"issue":"10","key":"604_CR23","doi-asserted-by":"publisher","first-page":"2193","DOI":"10.1109\/TASL.2013.2272524","volume":"21","author":"D Pavlidi","year":"2013","unstructured":"Pavlidi D, Griffin A, Puigt M, Mouchtaris A (2013) Real-time multiple sound source localization and counting using a circular microphone array. IEEE Trans Audio Speech Lang Process 21(10):2193\u20132206","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"604_CR24","unstructured":"Redmon J, Farhadi A (2018) Yolov3: An incremental improvement, arXiv preprint arXiv:1804.02767"},{"key":"604_CR25","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) Yolo9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp.\u00a07263\u20137271","DOI":"10.1109\/CVPR.2017.690"},{"key":"604_CR26","volume-title":"Learning OpenCV: computer vision with the OpenCV library","author":"G Bradski","year":"2008","unstructured":"Bradski G, Kaehler A (2008) Learning OpenCV: computer vision with the OpenCV library. O\u2019Reilly Media Inc, Sebastopol"},{"issue":"5","key":"604_CR27","doi-asserted-by":"publisher","first-page":"051205","DOI":"10.1117\/1.JEI.27.5.051205","volume":"27","author":"Y Ji","year":"2018","unstructured":"Ji Y, Wang S, Lu Y, Wei J, Zhao Y (2018) Eye and mouth state detection algorithm based on contour feature extraction. J Electron Imag 27(5):051205\u2013051205","journal-title":"J Electron Imag"},{"key":"604_CR28","doi-asserted-by":"crossref","unstructured":"Siddik MAD, Rahman MS (2023) Drowsiness and lethargy detection using machine learning techniques. In: 2023 International conference on electrical, computer and communication engineering (ECCE), 1\u20136","DOI":"10.1109\/ECCE57851.2023.10101607"},{"issue":"3","key":"604_CR29","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/0146-664X(80)90054-4","volume":"14","author":"P-E Danielsson","year":"1980","unstructured":"Danielsson P-E (1980) Euclidean distance mapping. Comput Graphics Image Process 14(3):227\u2013248","journal-title":"Comput Graphics Image Process"},{"key":"604_CR30","unstructured":"Grishchenko I, Ablavatski A, Kartynnik Y, Raveendran K, Grundmann M (2020) Attention mesh: high-fidelity face mesh prediction in real-time, arXiv preprint arXiv:2006.10962"},{"key":"604_CR31","doi-asserted-by":"crossref","unstructured":"Kazemi V, Sullivan J (2014) One millisecond face alignment with an ensemble of regression trees. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 1867\u20131874","DOI":"10.1109\/CVPR.2014.241"},{"key":"604_CR32","unstructured":"Kartynnik Y, Ablavatski A, Grishchenko I, Grundmann M (2019) Real-time facial surface geometry from monocular video on mobile gpus, arXiv preprint arXiv:1907.06724"},{"key":"604_CR33","unstructured":"Mingwu R, Han S (2005) A practical method for moving target detection under complex background, Computer Engineering, 33\u201334"},{"key":"604_CR34","doi-asserted-by":"crossref","unstructured":"Husein AM, Calvin Halim D, Leo R, William, (2019) Motion detect application with frame difference method on a surveillance camera. J Phys: Conf Ser 1230:012017","DOI":"10.1088\/1742-6596\/1230\/1\/012017"},{"key":"604_CR35","unstructured":"Sipeed-Wiki, \u201cSipeed maix r6+1 microphone array.\u201d https:\/\/wiki.sipeed.com\/hardware\/en\/modules\/micarray.html?highlight=6+1, Jun, 2022. [Online]"},{"key":"604_CR36","unstructured":"Sipeed-Wiki, \u201cSipeed maix dock (m1w).\u201d https:\/\/wiki.sipeed.com\/hardware\/en\/maix\/maixpy_develop_kit_board\/Maix_dock.html, Nov, 2020. [Online]"}],"container-title":["Intelligent Service Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11370-025-00604-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11370-025-00604-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11370-025-00604-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T15:40:25Z","timestamp":1757173225000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11370-025-00604-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":36,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["604"],"URL":"https:\/\/doi.org\/10.1007\/s11370-025-00604-2","relation":{},"ISSN":["1861-2776","1861-2784"],"issn-type":[{"value":"1861-2776","type":"print"},{"value":"1861-2784","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]},"assertion":[{"value":"29 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 July 2025","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The original version of this article was revised due to incorrect affiliations of the authors. Now it has been corrected.","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}}]}}