乐胖代购免代理版

{"id":"https://openalex.org/W3009035583","doi":"https://doi.org/10.1109/asru46091.2019.9003899","title":"Listening While Speaking and Visualizing: Improving ASR Through Multimodal Chain","display_name":"Listening While Speaking and Visualizing: Improving ASR Through Multimodal Chain","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3009035583","doi":"https://doi.org/10.1109/asru46091.2019.9003899","mag":"3009035583"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003899","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1906.00579","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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Johanes Effendi","raw_affiliation_strings":["RIKEN, Center for Advanced Intelligence Project AIP, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP, 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":"funder","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Andros Tjandra","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, 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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["RIKEN, Center for Advanced Intelligence Project AIP, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP, 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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["RIKEN, Center for Advanced Intelligence Project AIP, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP, Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.33,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.363756,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":79,"max":81},"biblio":{"volume":null,"issue":null,"first_page":"471","last_page":"478"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9992,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9992,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991,"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/T11309","display_name":"Music and Audio Processing","score":0.9968,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/closed-captioning","display_name":"Closed captioning","score":0.69355243}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.81880045},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.69355243},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.66757977},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5797485},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4954337},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47756487},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45783663},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33309764},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.071716756},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003899","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1906.00579","pdf_url":"https://arxiv.org/pdf/1906.00579","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1906.00579","pdf_url":"https://arxiv.org/pdf/1906.00579","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"display_name":"Quality education","score":0.41,"id":"https://metadata.un.org/sdg/4"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":33,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1524333225","https://openalex.org/W1686810756","https://openalex.org/W1773149199","https://openalex.org/W1916445035","https://openalex.org/W2024490156","https://openalex.org/W21006490","https://openalex.org/W2120847449","https://openalex.org/W2194775991","https://openalex.org/W2327501763","https://openalex.org/W2465870074","https://openalex.org/W2526425061","https://openalex.org/W2546938941","https://openalex.org/W2551572271","https://openalex.org/W2598581049","https://openalex.org/W2773827481","https://openalex.org/W2884852625","https://openalex.org/W2890952074","https://openalex.org/W2906048284","https://openalex.org/W2911708970","https://openalex.org/W2916979304","https://openalex.org/W2951939904","https://openalex.org/W2952746495","https://openalex.org/W2962699523","https://openalex.org/W2962793481","https://openalex.org/W2962835968","https://openalex.org/W2963266252","https://openalex.org/W2963295405","https://openalex.org/W2963444790","https://openalex.org/W2963581463","https://openalex.org/W2963609956","https://openalex.org/W2963796886","https://openalex.org/W2964048171"],"related_works":["https://openalex.org/W4380190185","https://openalex.org/W4298897568","https://openalex.org/W4290852288","https://openalex.org/W4289422896","https://openalex.org/W4210416330","https://openalex.org/W3217388757","https://openalex.org/W3215212336","https://openalex.org/W3164229987","https://openalex.org/W3122720459","https://openalex.org/W1938708284"],"abstract_inverted_index":{"Previously,":[0],"a":[1,90,102,113,118,123,139,152],"machine":[2],"speech":[3,16,30,55,61,83,172],"chain,":[4,185],"which":[5,186],"is":[6,58,69],"based":[7],"on":[8],"sequence-to-sequence":[9],"deep":[10],"learning,":[11],"was":[12],"proposed":[13,184],"to":[14,41,60],"mimic":[15],"perception":[17],"and":[18,26,33,37,62,72,76,116,121,134,173,176],"production":[19,136],"behavior.":[20],"Such":[21],"chains":[22],"separately":[23],"processed":[24],"listening":[25],"speaking":[27],"by":[28],"automatic":[29],"recognition":[31],"(ASR)":[32],"text-to-speech":[34],"synthesis":[35],"(TTS)":[36],"simultaneously":[38],"enabled":[39],"them":[40],"teach":[42],"each":[43,148],"other":[44],"in":[45,96],"semi-supervised":[46],"learning":[47],"when":[48],"they":[49],"received":[50],"unpaired":[51,106],"data.":[52,107,158],"Unfortunately,":[53],"this":[54,97,109],"chain":[56,84,120,126],"study":[57],"limited":[59],"textual":[63],"modalities.":[64],"In":[65,108],"fact,":[66],"natural":[67],"communication":[68],"actually":[70],"multimodal":[71,119,157],"involves":[73],"both":[74],"auditory":[75],"visual":[77],"sensory":[78],"systems.":[79],"Although":[80],"the":[81,86,145,188],"said":[82],"reduces":[85],"requirement":[87],"of":[88,93,105,147,155],"having":[89],"full":[91],"amount":[92,104],"paired":[94],"data,":[95],"case":[98],"we":[99,111],"still":[100],"need":[101],"large":[103,153],"research,":[110],"take":[112],"further":[114,169],"step":[115],"construct":[117],"design":[122],"closely":[124],"knit":[125],"architecture":[127],"that":[128,164],"combines":[129],"ASR,":[130],"TTS,":[131],"image":[132,135],"captioning,":[133],"models":[137],"into":[138],"single":[140],"framework.":[141],"The":[142],"framework":[143],"allows":[144],"training":[146],"component":[149],"without":[150,171],"requiring":[151],"number":[154],"parallel":[156],"Our":[159],"experimental":[160],"results":[161],"also":[162],"show":[163],"an":[165],"ASR":[166,189],"can":[167],"be":[168],"trained":[170],"text":[174],"data":[175,178],"cross-modal":[177],"augmentation":[179],"remains":[180],"possible":[181],"through":[182],"our":[183],"improves":[187],"performance.":[190]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3009035583","counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2025-02-25T11:08:54.213589","created_date":"2020-03-06"}