{"id":"https://openalex.org/W3155217823","doi":"https://doi.org/10.1109/access.2021.3071541","title":"End-to-End Image-to-Speech Generation for Untranscribed Unknown Languages","display_name":"End-to-End Image-to-Speech Generation for Untranscribed Unknown Languages","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3155217823","doi":"https://doi.org/10.1109/access.2021.3071541","mag":"3155217823"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3071541","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3071541","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09398708.pdf","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://ieeexplore.ieee.org/ielx7/6287639/9312710/09398708.pdf","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/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":3,"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":1.0681,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.78734852,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"9","issue":null,"first_page":"55144","last_page":"55154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9941999912261963,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9922999739646912,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8617033958435059},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.83014976978302},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6576460003852844},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6564094424247742},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6263689994812012},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6042459011077881},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5559873580932617},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5343579053878784},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.517212986946106},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4783627390861511},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4678434133529663},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45350220799446106},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.41665107011795044},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.414381742477417},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.33820199966430664}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8617033958435059},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.83014976978302},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6576460003852844},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6564094424247742},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6263689994812012},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6042459011077881},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5559873580932617},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5343579053878784},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.517212986946106},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4783627390861511},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4678434133529663},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45350220799446106},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.41665107011795044},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.414381742477417},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33820199966430664},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/access.2021.3071541","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3071541","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09398708.pdf","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:c338ef671b0948cbb607626237349258","is_oa":true,"landing_page_url":"https://doaj.org/article/c338ef671b0948cbb607626237349258","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 55144-55154 (2021)","raw_type":"article"},{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005782728","is_oa":false,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4277","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:10061/14268","is_oa":true,"landing_page_url":"http://hdl.handle.net/10061/14268","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.2021.3071541","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3071541","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09398708.pdf","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":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1688345242","display_name":null,"funder_award_id":"17H06101","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3459562248","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5256887504","display_name":null,"funder_award_id":"Japan Society for the Promotion of Science (JSPS)","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"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/G7752643416","display_name":null,"funder_award_id":"Japan","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3155217823.pdf","grobid_xml":"https://content.openalex.org/works/W3155217823.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1956340063","https://openalex.org/W1959608418","https://openalex.org/W2057007397","https://openalex.org/W2079460648","https://openalex.org/W2101105183","https://openalex.org/W2117041980","https://openalex.org/W2119775030","https://openalex.org/W2120847449","https://openalex.org/W2122538988","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2170659185","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2327501763","https://openalex.org/W2345811097","https://openalex.org/W2347098582","https://openalex.org/W2347145335","https://openalex.org/W2398490608","https://openalex.org/W2556930864","https://openalex.org/W2752796333","https://openalex.org/W2940544976","https://openalex.org/W2951444698","https://openalex.org/W2962862718","https://openalex.org/W2963403868","https://openalex.org/W2963609956","https://openalex.org/W2963620343","https://openalex.org/W2963799213","https://openalex.org/W2963909453","https://openalex.org/W2964115348","https://openalex.org/W2964121744","https://openalex.org/W2972374322","https://openalex.org/W2973026522","https://openalex.org/W3007068036","https://openalex.org/W3009205145","https://openalex.org/W3093096176","https://openalex.org/W3093427098","https://openalex.org/W3096216486","https://openalex.org/W3096249149","https://openalex.org/W3114436296","https://openalex.org/W3174311593","https://openalex.org/W4206865574","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6682631176","https://openalex.org/W6729977899","https://openalex.org/W6739901393","https://openalex.org/W6787100281"],"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/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W3009270862"],"abstract_inverted_index":{"Describing":[0],"orally":[1],"what":[2],"we":[3,10,54],"are":[4,94],"seeing":[5],"is":[6],"a":[7,31,72,84,132],"simple":[8,24],"task":[9,25],"do":[11],"in":[12,17,42,48,67,87],"our":[13,138,152],"daily":[14],"life.":[15],"However,":[16],"the":[18,36,43,80,105,112,122,125,146,157],"natural":[19,134],"language":[20],"processing":[21],"field,":[22],"this":[23,52],"needs":[26],"to":[27,38,78,108,145],"be":[28,109],"bridged":[29],"by":[30,96],"textual":[32,65,149],"modality":[33],"that":[34,60],"helps":[35],"system":[37,59],"generalize":[39],"various":[40,46],"objects":[41],"image":[44],"and":[45,164],"pronunciations":[47],"speech":[49,85,102,126,135],"utterances.":[50],"In":[51],"study,":[53],"propose":[55],"an":[56,88,97],"end-to-end":[57],"Image2Speech":[58,106,141,166],"does":[61],"not":[62],"need":[63],"any":[64],"information":[66],"its":[68],"training.":[69],"We":[70],"use":[71],"vector-quantized":[73],"variational":[74],"autoencoder":[75],"(VQ-VAE)":[76],"model":[77,107],"learn":[79],"discrete":[81,92],"representation":[82,103],"of":[83,115,124],"caption":[86],"unsupervised":[89],"manner,":[90],"where":[91],"labels":[93],"used":[95],"image-captioning":[98],"model.":[99],"This":[100],"self-supervised":[101],"enables":[104],"trained":[110],"with":[111,131,148,162],"minimum":[113],"amount":[114],"paired":[116],"image-speech":[117],"data":[118],"while":[119],"still":[120],"maintaining":[121],"quality":[123],"caption.":[127],"Our":[128],"experimental":[129],"results":[130],"multi-speaker":[133],"dataset":[136],"demonstrate":[137],"proposed":[139],"text-free":[140],"system's":[142],"performance":[143],"close":[144],"one":[147],"information.":[150],"Furthermore,":[151],"approach":[153],"also":[154],"successfully":[155],"outperforms":[156],"most":[158],"recent":[159],"existing":[160],"frameworks":[161],"phoneme-based":[163],"grounding-based":[165],"systems.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
