{"id":"https://openalex.org/W3123798147","doi":"https://doi.org/10.1109/taslp.2021.3053391","title":"Generating Images From Spoken Descriptions","display_name":"Generating Images From Spoken Descriptions","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3123798147","doi":"https://doi.org/10.1109/taslp.2021.3053391","mag":"3123798147"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3053391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3053391","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://resolver.tudelft.nl/uuid:b1ba78ac-15c9-4e79-b978-d58c720810b2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021472684","display_name":"Xinsheng Wang","orcid":"https://orcid.org/0000-0003-1826-7419"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["CN","NL"],"is_corresponding":true,"raw_author_name":"Xinsheng Wang","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology, Delft, CD, The Netherlands","School of Software Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, China","School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"School of Software Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102776486","display_name":"Tingting Qiao","orcid":"https://orcid.org/0000-0002-2045-1170"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["CN","NL"],"is_corresponding":false,"raw_author_name":"Tingting Qiao","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China","Multimedia Computing Group, Delft University of Technology, Delft, CD, The Netherlands"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068185614","display_name":"Jihua Zhu","orcid":"https://orcid.org/0000-0002-3081-8781"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihua Zhu","raw_affiliation_strings":["School of Software Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, China","School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037486611","display_name":"Alan Hanjali\u0107","orcid":"https://orcid.org/0000-0002-5771-2549"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Alan Hanjalic","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology, Delft, CD, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048860892","display_name":"Odette Scharenborg","orcid":"https://orcid.org/0000-0003-0693-8852"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Odette Scharenborg","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology, Delft, CD, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5021472684"],"corresponding_institution_ids":["https://openalex.org/I87445476","https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":2.0391,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.88494102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"29","issue":null,"first_page":"850","last_page":"865"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9904000163078308,"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":0.9876999855041504,"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/computer-science","display_name":"Computer science","score":0.8004238605499268},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.593961238861084},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.5747379064559937},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5634148120880127},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5043641328811646},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.49390679597854614},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4910140335559845},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4800321161746979},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4670141339302063},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46013110876083374},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4439806044101715},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3279059827327728},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11820557713508606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8004238605499268},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.593961238861084},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.5747379064559937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5634148120880127},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5043641328811646},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.49390679597854614},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4910140335559845},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4800321161746979},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4670141339302063},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46013110876083374},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4439806044101715},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3279059827327728},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11820557713508606},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2021.3053391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3053391","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:tud:oai:tudelft.nl:uuid:b1ba78ac-15c9-4e79-b978-d58c720810b2","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:b1ba78ac-15c9-4e79-b978-d58c720810b2","pdf_url":"http://resolver.tudelft.nl/uuid:b1ba78ac-15c9-4e79-b978-d58c720810b2","source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE - ACM Transactions on Audio, Speech, and Language Processing, 29","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:tud:oai:tudelft.nl:uuid:b1ba78ac-15c9-4e79-b978-d58c720810b2","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:b1ba78ac-15c9-4e79-b978-d58c720810b2","pdf_url":"http://resolver.tudelft.nl/uuid:b1ba78ac-15c9-4e79-b978-d58c720810b2","source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE - ACM Transactions on Audio, Speech, and Language Processing, 29","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6399999856948853,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2300736770","display_name":null,"funder_award_id":"(CSC)","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G6740317072","display_name":null,"funder_award_id":"2018AAA0102504","funder_id":"https://openalex.org/F4320336026","funder_display_name":"National Key Research and Development Program of China Stem Cell and Translational Research"},{"id":"https://openalex.org/G8589651859","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320336026","display_name":"National Key Research and Development Program of China Stem Cell and Translational Research","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3123798147.pdf"},"referenced_works_count":78,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1797268635","https://openalex.org/W1905882502","https://openalex.org/W2099471712","https://openalex.org/W2117539524","https://openalex.org/W2125389028","https://openalex.org/W2134670479","https://openalex.org/W2157331557","https://openalex.org/W2183341477","https://openalex.org/W2187089797","https://openalex.org/W2398118205","https://openalex.org/W2405756170","https://openalex.org/W2533598788","https://openalex.org/W2556930864","https://openalex.org/W2731516742","https://openalex.org/W2888867175","https://openalex.org/W2895743108","https://openalex.org/W2916113431","https://openalex.org/W2922538097","https://openalex.org/W2924476266","https://openalex.org/W2927673779","https://openalex.org/W2949999304","https://openalex.org/W2950133079","https://openalex.org/W2962845008","https://openalex.org/W2962862718","https://openalex.org/W2963163163","https://openalex.org/W2963259843","https://openalex.org/W2963300588","https://openalex.org/W2963373786","https://openalex.org/W2963444790","https://openalex.org/W2963612019","https://openalex.org/W2963902314","https://openalex.org/W2963966654","https://openalex.org/W2963981733","https://openalex.org/W2964024144","https://openalex.org/W2964243274","https://openalex.org/W2965289598","https://openalex.org/W2970903655","https://openalex.org/W2971709506","https://openalex.org/W2979157532","https://openalex.org/W2979571231","https://openalex.org/W2988907666","https://openalex.org/W2989607414","https://openalex.org/W2995521531","https://openalex.org/W2995665739","https://openalex.org/W2999894541","https://openalex.org/W2999966482","https://openalex.org/W3003440718","https://openalex.org/W3005578234","https://openalex.org/W3009811209","https://openalex.org/W3015215494","https://openalex.org/W3015580115","https://openalex.org/W3035575271","https://openalex.org/W3036914231","https://openalex.org/W3095030004","https://openalex.org/W3102219307","https://openalex.org/W3154807520","https://openalex.org/W3201409833","https://openalex.org/W4300406642","https://openalex.org/W4320013936","https://openalex.org/W6631362777","https://openalex.org/W6638319203","https://openalex.org/W6678815747","https://openalex.org/W6679792166","https://openalex.org/W6713645886","https://openalex.org/W6718379498","https://openalex.org/W6729977899","https://openalex.org/W6745554073","https://openalex.org/W6765779288","https://openalex.org/W6767936260","https://openalex.org/W6770208262","https://openalex.org/W6772157574","https://openalex.org/W6772649462","https://openalex.org/W6773249456","https://openalex.org/W6780603694","https://openalex.org/W6917585676"],"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/W4289422896"],"abstract_inverted_index":{"Text-based":[0],"technologies,":[1],"such":[2],"as":[3,86],"text":[4,68],"translation":[5],"from":[6,39,77,114,215],"one":[7],"language":[8],"to":[9,26,61,74,85],"another,":[10],"and":[11,94,164,173,192,196,212,223],"image":[12],"captioning,":[13],"are":[14,24,135,145,155,181],"gaining":[15],"popularity.":[16],"However,":[17],"approximately":[18],"half":[19],"of":[20,89,110,187,190,205],"the":[21,108,125,130,139,185,203,206,216,228],"world's":[22],"languages":[23,36,73],"estimated":[25],"be":[27],"lacking":[28],"a":[29,46,52,90,95,220,224],"commonly":[30,156],"used":[31,157,183],"written":[32],"form.":[33],"Consequently,":[34],"these":[35,200],"cannot":[37],"benefit":[38,76],"text-based":[40],"technologies.":[41],"This":[42],"paper":[43],"presents":[44],"1)":[45],"new":[47],"speech":[48,59,91,101,105,126,131,171,178,191,217],"technology":[49],"task,":[50],"i.e.,":[51,162,194],"speech-to-image":[53,82],"generation":[54,160],"(S2IG)":[55],"framework":[56],"which":[57,167,180],"translates":[58],"descriptions":[60,179],"photo-realistic":[62],"images":[63,214],"2)":[64],"without":[65],"using":[66],"any":[67],"information,":[69],"thus":[70],"allowing":[71],"unwritten":[72],"potentially":[75],"this":[78],"technology.":[79],"The":[80,100,116],"proposed":[81,207],"framework,":[83],"referred":[84],"S2IGAN,":[87],"consists":[88],"embedding":[92,102,132],"network":[93,103],"relation-supervised":[96,117],"densely-stacked":[97,118],"generative":[98,119],"model.":[99],"learns":[104],"embeddings":[106,127],"with":[107,138,176],"supervision":[109],"corresponding":[111,140],"visual":[112],"information":[113],"images.":[115],"model":[120],"synthesizes":[121],"images,":[122,193],"conditioned":[123],"on":[124,147,199,209],"produced":[128],"by":[129],"network,":[133],"that":[134,154],"semantically":[136],"consistent":[137],"spoken":[141],"descriptions.":[142],"Extensive":[143],"experiments":[144],"conducted":[146],"four":[148],"public":[149],"benchmark":[150],"databases:":[151],"two":[152,174],"databases":[153,175,201],"in":[158,184],"text-to-image":[159],"tasks,":[161],"CUB-200":[163],"Oxford-102":[165],"for":[166,227],"we":[168],"created":[169],"synthesized":[170],"descriptions,":[172],"natural":[177],"often":[182],"field":[186],"cross-modal":[188],"learning":[189],"Flickr8k":[195],"Places.":[197],"Results":[198],"demonstrate":[202],"effectiveness":[204],"S2IGAN":[208],"synthesizing":[210],"high-quality":[211],"semantically-consistent":[213],"signal,":[218],"yielding":[219],"good":[221],"performance":[222],"solid":[225],"baseline":[226],"S2IG":[229],"task.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}