{"id":"https://openalex.org/W3095030004","doi":"https://doi.org/10.21437/interspeech.2020-1759","title":"S2IGAN: Speech-to-Image Generation via Adversarial Learning","display_name":"S2IGAN: Speech-to-Image Generation via Adversarial Learning","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095030004","doi":"https://doi.org/10.21437/interspeech.2020-1759","mag":"3095030004"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1759","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1759","pdf_url":"https://www.isca-archive.org/interspeech_2020/wang20x_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2020/wang20x_interspeech.pdf","any_repository_has_fulltext":null},"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":false,"raw_author_name":"Xinsheng Wang","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands","School of Software Engineering, Xi'an Jiaotong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, 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":["Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands","College of Computer Science and Technology, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I168879160"]}]},{"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'an Jiaotong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, 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, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, 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, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2292","last_page":"2296"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9639000296592712,"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":0.9639000296592712,"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":0.9625999927520752,"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/T10860","display_name":"Speech and Audio Processing","score":0.9437000155448914,"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/adversarial-system","display_name":"Adversarial system","score":0.8269345164299011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7380608916282654},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5565372705459595},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5367897748947144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5175139904022217},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3665943741798401}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8269345164299011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7380608916282654},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5565372705459595},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5367897748947144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5175139904022217},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3665943741798401}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-1759","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1759","pdf_url":"https://www.isca-archive.org/interspeech_2020/wang20x_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:tudelft.nl:uuid:3fdef35c-3548-4298-820a-935769098224","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:3fdef35c-3548-4298-820a-935769098224","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2020-1759","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1759","pdf_url":"https://www.isca-archive.org/interspeech_2020/wang20x_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3095030004.pdf","grobid_xml":"https://content.openalex.org/works/W3095030004.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1797268635","https://openalex.org/W2117539524","https://openalex.org/W2125389028","https://openalex.org/W2157331557","https://openalex.org/W2183341477","https://openalex.org/W2398118205","https://openalex.org/W2405756170","https://openalex.org/W2533598788","https://openalex.org/W2927673779","https://openalex.org/W2963373786","https://openalex.org/W2963612019","https://openalex.org/W2963966654","https://openalex.org/W2964243274","https://openalex.org/W2966421984","https://openalex.org/W2970903655","https://openalex.org/W2971709506","https://openalex.org/W2979157532","https://openalex.org/W3009811209","https://openalex.org/W3015215494","https://openalex.org/W4296979096","https://openalex.org/W4297606427","https://openalex.org/W4301206121","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W2903917280","https://openalex.org/W4205705013","https://openalex.org/W2901368259","https://openalex.org/W3198184493","https://openalex.org/W1858327386","https://openalex.org/W2789919619","https://openalex.org/W2293457016","https://openalex.org/W4295850094","https://openalex.org/W2351428524","https://openalex.org/W4304891817"],"abstract_inverted_index":{"An":[0],"estimated":[1],"half":[2],"of":[3,63,83,118],"the":[4,77,81,84,89,95,105,116,119,129,141],"world's":[5],"languages":[6,18,50],"do":[7],"not":[8],"have":[9],"a":[10,28,64,70,133,137],"written":[11],"form,":[12],"making":[13],"it":[14],"impossible":[15],"for":[16,140],"these":[17],"to":[19,39,51],"benefit":[20,53],"from":[21,54,128],"any":[22,44],"existing":[23],"text-based":[24],"technologies.In":[25],"this":[26,55],"paper,":[27],"speech-toimage":[29],"generation":[30],"(S2IG)":[31],"framework":[32],"is":[33],"proposed":[34,57,96,120],"which":[35],"translates":[36],"speech":[37,65,78,90,107,130],"descriptions":[38],"photo-realistic":[40],"images":[41,99,127],"without":[42],"using":[43],"text":[45],"information,":[46],"thus":[47],"allowing":[48],"unwritten":[49],"potentially":[52],"technology.The":[56],"S2IG":[58,142],"framework,":[59],"named":[60],"S2IGAN,":[61],"consists":[62],"embedding":[66,79,91],"network":[67],"(SEN)":[68],"and":[69,113,125,136],"relation-supervised":[71],"densely-stacked":[72],"generative":[73],"model":[74],"(RDG).SEN":[75],"learns":[76],"with":[80,104],"supervision":[82],"corresponding":[85,106],"visual":[86],"information.Conditioned":[87],"on":[88,110,122],"produced":[92],"by":[93],"SEN,":[94],"RDG":[97],"synthesizes":[98],"that":[100],"are":[101],"semantically":[102],"consistent":[103],"descriptions.Extensive":[108],"experiments":[109],"datasets":[111],"CUB":[112],"Oxford-102":[114],"demonstrate":[115],"effectiveness":[117],"S2IGAN":[121],"synthesizing":[123],"high-quality":[124],"semantically-consistent":[126],"signal,":[131],"yielding":[132],"good":[134],"performance":[135],"solid":[138],"baseline":[139],"task.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}