{"id":"https://openalex.org/W4387677973","doi":"https://doi.org/10.1109/icac57885.2023.10275158","title":"Study on Adoption of 3D Computer Vision and Speech Recognition in Intelligent Manufacturing","display_name":"Study on Adoption of 3D Computer Vision and Speech Recognition in Intelligent Manufacturing","publication_year":2023,"publication_date":"2023-08-30","ids":{"openalex":"https://openalex.org/W4387677973","doi":"https://doi.org/10.1109/icac57885.2023.10275158"},"language":"en","primary_location":{"id":"doi:10.1109/icac57885.2023.10275158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icac57885.2023.10275158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 28th International Conference on Automation and Computing (ICAC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100406666","display_name":"Quan Zhang","orcid":"https://orcid.org/0000-0001-7778-4243"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Quan Zhang","raw_affiliation_strings":["School of Advanced Technology, Xi &#x0027;an Jiaotong-Liverpool University,Suzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi &#x0027;an Jiaotong-Liverpool University,Suzhou,China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031639393","display_name":"Yuliang Xiao","orcid":"https://orcid.org/0000-0003-0244-971X"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuliang Xiao","raw_affiliation_strings":["School of Advanced Technology, Xi &#x0027;an Jiaotong-Liverpool University,Suzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi &#x0027;an Jiaotong-Liverpool University,Suzhou,China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074787389","display_name":"Mark Leach","orcid":"https://orcid.org/0000-0002-7874-2376"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mark Leach","raw_affiliation_strings":["School of Advanced Technology, Xi &#x0027;an Jiaotong-Liverpool University,Suzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi &#x0027;an Jiaotong-Liverpool University,Suzhou,China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033755146","display_name":"Eng Gee Lim","orcid":"https://orcid.org/0000-0003-0199-7386"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enggee Lim","raw_affiliation_strings":["School of Advanced Technology, Xi &#x0027;an Jiaotong-Liverpool University,Suzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi &#x0027;an Jiaotong-Liverpool University,Suzhou,China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052409500","display_name":"Fangrui Guo","orcid":"https://orcid.org/0009-0008-0165-2701"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangrui Guo","raw_affiliation_strings":["School of Advanced Technology, Xi &#x0027;an Jiaotong-Liverpool University,Suzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi &#x0027;an Jiaotong-Liverpool University,Suzhou,China","institution_ids":["https://openalex.org/I69356397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100406666"],"corresponding_institution_ids":["https://openalex.org/I69356397"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12995241,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9864000082015991,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/workstation","display_name":"Workstation","score":0.8579171895980835},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.786159873008728},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.6122195720672607},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5225526690483093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4982128143310547},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4878826141357422},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.48412832617759705},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4812609851360321},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47171443700790405},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.45292460918426514}],"concepts":[{"id":"https://openalex.org/C67953723","wikidata":"https://www.wikidata.org/wiki/Q192525","display_name":"Workstation","level":2,"score":0.8579171895980835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.786159873008728},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.6122195720672607},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5225526690483093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4982128143310547},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4878826141357422},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48412832617759705},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4812609851360321},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47171443700790405},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.45292460918426514},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icac57885.2023.10275158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icac57885.2023.10275158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 28th International Conference on Automation and Computing (ICAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1525408973","https://openalex.org/W1637570796","https://openalex.org/W1686810756","https://openalex.org/W1689711448","https://openalex.org/W1842393320","https://openalex.org/W1980748436","https://openalex.org/W2124530615","https://openalex.org/W2167276710","https://openalex.org/W2193145675","https://openalex.org/W2545666978","https://openalex.org/W2591641731","https://openalex.org/W2887784216","https://openalex.org/W2963037989","https://openalex.org/W3017086313","https://openalex.org/W3106250896","https://openalex.org/W3169493307","https://openalex.org/W4377164392","https://openalex.org/W6636885848","https://openalex.org/W6637373629","https://openalex.org/W6678640178"],"related_works":["https://openalex.org/W2045348955","https://openalex.org/W2352028719","https://openalex.org/W2584886384","https://openalex.org/W2378667902","https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2791088446","https://openalex.org/W2097963413","https://openalex.org/W2052769075","https://openalex.org/W2026311529"],"abstract_inverted_index":{"This":[0],"work":[1],"aims":[2],"to":[3,138],"adopt":[4],"state-of-art,":[5],"artificial":[6],"intelligence":[7],"(AI)":[8],"based":[9],"technology":[10],"in":[11,16,48,114,121],"intelligent":[12,31],"manufacturing":[13,32],"applications,":[14],"which":[15,81],"involve":[17],"using":[18,69],"3D":[19,66],"computer":[20],"vison":[21],"and":[22,79,105,119,141],"speech":[23,92],"recognition":[24,96,108],"(voice":[25],"commands)":[26],"for":[27,76,131],"control":[28],"of":[29,116],"typical":[30],"systems":[33],"such":[34],"as":[35,125,127],"robotic":[36,133],"workstations.":[37],"As":[38],"a":[39,44,54,65,91],"first":[40],"attempt,":[41],"we":[42,62],"consider":[43],"relatively":[45],"simple":[46],"scenario":[47],"manufacturing,":[49],"i.e.":[50],"object":[51,77],"grasping,":[52],"with":[53,98],"3-axis":[55],"Cartesian":[56],"robot":[57],"arm.":[58],"On":[59],"this":[60],"workstation,":[61],"have":[63,88],"developed":[64,90],"vision":[67],"system":[68,97,140],"the":[70],"Intel":[71],"RealSense":[72],"D455":[73],"depth":[74],"camera":[75],"detection":[78],"capture,":[80],"is":[82,112],"processed":[83],"by":[84],"SSD":[85],"algorithm.":[86],"We":[87],"also":[89],"(audio":[93],"or":[94],"voice)":[95],"our":[99,132,139],"proposed":[100],"algorithm,":[101],"combining":[102],"both":[103,117],"LSTM":[104],"GMM-HMM":[106],"audio":[107],"models.":[109],"Good":[110],"performance":[111],"achieved":[113],"terms":[115],"efficiency":[118],"accuracy":[120],"controlling":[122],"normal":[123],"operation,":[124],"well":[126],"emergency":[128],"stop":[129],"functionality":[130],"workstation.":[134],"Possible":[135],"future":[136],"improvements":[137],"relevant":[142],"methodology":[143],"are":[144],"discussed.":[145]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
