{"id":"https://openalex.org/W3157555801","doi":"https://doi.org/10.1109/access.2021.3077886","title":"Multimodal Chain: Cross-Modal Collaboration Through Listening, Speaking, and Visualizing","display_name":"Multimodal Chain: Cross-Modal Collaboration Through Listening, Speaking, and Visualizing","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3157555801","doi":"https://doi.org/10.1109/access.2021.3077886","mag":"3157555801"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3077886","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3077886","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2021.3077886","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091846449","display_name":"Johanes Effendi","orcid":"https://orcid.org/0000-0001-5755-415X"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Johanes Effendi","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma, Japan","RIKEN, Center for Advanced Intelligence Project AIP, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038296765","display_name":"Andros Tjandra","orcid":"https://orcid.org/0000-0003-1246-5908"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Andros Tjandra","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma, Japan","RIKEN, Center for Advanced Intelligence Project AIP, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma, Japan","RIKEN, Center for Advanced Intelligence Project AIP, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091846449"],"corresponding_institution_ids":["https://openalex.org/I4210126580","https://openalex.org/I75917431"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.1942,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46900653,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"9","issue":null,"first_page":"70286","last_page":"70299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9986000061035156,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9986000061035156,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9948999881744385,"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8330916166305542},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.70817631483078},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6281390190124512},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5516140460968018},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5048075914382935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44628190994262695},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4226512610912323},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3513893485069275},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3487395644187927},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.29661309719085693},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.09392330050468445}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8330916166305542},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.70817631483078},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6281390190124512},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5516140460968018},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5048075914382935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44628190994262695},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4226512610912323},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3513893485069275},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3487395644187927},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29661309719085693},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.09392330050468445},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/access.2021.3077886","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3077886","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:54783d59c0a54870a577e51ff651eef8","is_oa":true,"landing_page_url":"https://doaj.org/article/54783d59c0a54870a577e51ff651eef8","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 70286-70299 (2021)","raw_type":"article"},{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005782733","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4282","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access","raw_type":"journal article"},{"id":"pmh:oai:library.naist.jp:10061/14302","is_oa":true,"landing_page_url":"http://hdl.handle.net/10061/14302","pdf_url":null,"source":{"id":"https://openalex.org/S4377196843","display_name":"NAIST Digital Library (Nara Institute of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I75917431","host_organization_name":"Nara Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I75917431"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3077886","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3077886","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6100000143051147,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G6616750388","display_name":null,"funder_award_id":"JP17H06101","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7236939988","display_name":null,"funder_award_id":"JP21H03467","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1630959083","https://openalex.org/W1773149199","https://openalex.org/W1982992068","https://openalex.org/W2007428019","https://openalex.org/W2014621385","https://openalex.org/W2024490156","https://openalex.org/W2101105183","https://openalex.org/W2133564696","https://openalex.org/W2194775991","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2546938941","https://openalex.org/W2551572271","https://openalex.org/W2586850765","https://openalex.org/W2612434969","https://openalex.org/W2803775694","https://openalex.org/W2884852625","https://openalex.org/W2890952074","https://openalex.org/W2906048284","https://openalex.org/W2911708970","https://openalex.org/W2946856970","https://openalex.org/W2951939904","https://openalex.org/W2952746495","https://openalex.org/W2962699523","https://openalex.org/W2962793481","https://openalex.org/W2962824366","https://openalex.org/W2963295405","https://openalex.org/W2963373786","https://openalex.org/W2963444790","https://openalex.org/W2963581463","https://openalex.org/W2963609956","https://openalex.org/W2963796886","https://openalex.org/W2963966654","https://openalex.org/W2978661203","https://openalex.org/W2981952041","https://openalex.org/W2990113535","https://openalex.org/W3009035583","https://openalex.org/W3009565979","https://openalex.org/W3096246310","https://openalex.org/W3106776857","https://openalex.org/W6636599907","https://openalex.org/W6679434410","https://openalex.org/W6718379498","https://openalex.org/W6729383884","https://openalex.org/W6735204497","https://openalex.org/W6737575990","https://openalex.org/W6741328424","https://openalex.org/W6751511662","https://openalex.org/W6754392867","https://openalex.org/W6763015118"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4290852288","https://openalex.org/W2199184806","https://openalex.org/W127837312","https://openalex.org/W2922283411","https://openalex.org/W4384789578","https://openalex.org/W4387421317"],"abstract_inverted_index":{"Language":[0],"is":[1,10,83,123],"an":[2,22,203,208],"integral":[3],"part":[4],"of":[5,25,93,102,135,196,215],"human":[6,104],"interpersonal":[7],"communication,":[8],"which":[9,31],"conveyed":[11],"through":[12,157],"multiple":[13],"sensory":[14],"channels.":[15],"This":[16],"multisensory":[17],"communication":[18],"skill":[19],"has":[20],"motivated":[21],"extensive":[23],"number":[24],"studies":[26],"on":[27],"multimodal":[28,113],"information":[29],"processing,":[30],"are":[32,66,96,139],"trying":[33],"to":[34,61,77],"develop":[35],"a":[36,91,112,117,171,178,190],"system":[37],"that":[38,122,167],"mimics":[39],"this":[40,82,100],"natural":[41],"behaviour.":[42],"For":[43],"example,":[44],"automatic":[45],"speech":[46,197],"recognition":[47],"(ASR)":[48],"represents":[49,54],"listening":[50],"activity,":[51],"text-to-speech":[52],"(TTS)":[53],"speaking,":[55],"and":[56,68,106,125,144,149,183,198],"various":[57],"image":[58,146,150],"processing":[59],"models":[60,152],"represent":[62],"visual":[63,107,199],"perception.":[64],"Most":[65],"trained":[67,124],"tuned":[69,126],"independently":[70],"using":[71,169],"parallel":[72],"examples":[73],"from":[74,186],"the":[75,78,85,103,133,194,213],"source":[76],"target":[79],"modality.":[80],"However,":[81],"not":[84],"case":[86],"in":[87,189],"real-life":[88],"situations,":[89],"where":[90],"lot":[92],"paired":[94,136],"data":[95,138,185],"unavailable.":[97],"Inspired":[98],"by":[99,168],"self-supervision":[101],"auditory":[105],"perception":[108],"system,":[109],"we":[110,175,201],"proposed":[111,130],"chain":[114,119,161,173],"mechanism":[115],"with":[116,180,207],"weakly-supervised":[118],"training":[120,137],"strategy":[121],"jointly.":[127],"In":[128],"our":[129],"framework,":[131],"when":[132],"amount":[134],"insufficient,":[140],"collaboration":[141,195],"among":[142],"ASR":[143,204],"TTS,":[145],"captioning":[147],"(IC),":[148],"production":[151],"can":[153,176],"improve":[154,177,202],"their":[155],"performance":[156,206,214],"single":[158],"or":[159],"dual-loop":[160],"mechanisms.":[162],"Our":[163],"experiment":[164],"result":[165],"showed":[166],"such":[170],"closed-loop":[172],"mechanism,":[174],"model":[179,205],"both":[181],"unpaired":[182],"unrelated":[184],"different":[187],"modalities":[188],"semi-supervised":[191],"manner.":[192],"Through":[193],"chains,":[200],"image-only":[209],"dataset":[210],"while":[211],"maintaining":[212],"other":[216],"models.":[217]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}