{"id":"https://openalex.org/W3143970329","doi":"https://doi.org/10.1109/icassp39728.2021.9413802","title":"Collaborative Learning to Generate Audio-Video Jointly","display_name":"Collaborative Learning to Generate Audio-Video Jointly","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3143970329","doi":"https://doi.org/10.1109/icassp39728.2021.9413802","mag":"3143970329"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413802","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.02656","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082361685","display_name":"Vinod K Kurmi","orcid":"https://orcid.org/0000-0003-0332-5647"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Vinod K Kurmi","raw_affiliation_strings":["Indian Institute of Technology Kanpur"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kanpur","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075644109","display_name":"Vipul Bajaj","orcid":null},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vipul Bajaj","raw_affiliation_strings":["Indian Institute of Technology Kanpur"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kanpur","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035714586","display_name":"Badri N. Patro","orcid":"https://orcid.org/0000-0002-2585-7014"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Badri N Patro","raw_affiliation_strings":["Indian Institute of Technology Kanpur"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kanpur","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103512058","display_name":"K. S. Venkatesh","orcid":null},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K S Venkatesh","raw_affiliation_strings":["Indian Institute of Technology Kanpur"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kanpur","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007109424","display_name":"Vinay P. Namboodiri","orcid":"https://orcid.org/0000-0001-5262-9722"},"institutions":[{"id":"https://openalex.org/I51601045","display_name":"University of Bath","ror":"https://ror.org/002h8g185","country_code":"GB","type":"education","lineage":["https://openalex.org/I51601045"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vinay P Namboodiri","raw_affiliation_strings":["University of Bath"],"affiliations":[{"raw_affiliation_string":"University of Bath","institution_ids":["https://openalex.org/I51601045"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036738038","display_name":"Preethi Jyothi","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Preethi Jyothi","raw_affiliation_strings":["Indian Institute of Technology Bombay"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5082361685"],"corresponding_institution_ids":["https://openalex.org/I94234084"],"apc_list":null,"apc_paid":null,"fwci":0.3078,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51591031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4180","last_page":"4184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9994000196456909,"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":0.9984999895095825,"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":0.8506438136100769},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6563507318496704},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6162384748458862},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.607858419418335},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5925247669219971},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4590749442577362},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4145164489746094},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3810085952281952}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8506438136100769},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6563507318496704},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6162384748458862},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.607858419418335},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5925247669219971},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4590749442577362},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4145164489746094},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3810085952281952},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413802","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.02656","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.02656","pdf_url":"https://arxiv.org/pdf/2104.02656","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":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":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3143970329","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2104.02656","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2104.02656","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.02656","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":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":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/xb9s-7v25","is_oa":true,"landing_page_url":"https://doi.org/10.17023/xb9s-7v25","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.02656","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.02656","pdf_url":"https://arxiv.org/pdf/2104.02656","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":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":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3143970329.pdf","grobid_xml":"https://content.openalex.org/works/W3143970329.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W2099471712","https://openalex.org/W2173520492","https://openalex.org/W2519091744","https://openalex.org/W2606176153","https://openalex.org/W2786254735","https://openalex.org/W2910577860","https://openalex.org/W2919624000","https://openalex.org/W2950299304","https://openalex.org/W2951535099","https://openalex.org/W2951611190","https://openalex.org/W2962760235","https://openalex.org/W2962960500","https://openalex.org/W2963066677","https://openalex.org/W2963092440","https://openalex.org/W2963115079","https://openalex.org/W2963218389","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2963474063","https://openalex.org/W2963663420","https://openalex.org/W2963680395","https://openalex.org/W2963807156","https://openalex.org/W2963890275","https://openalex.org/W2963902314","https://openalex.org/W2964345931","https://openalex.org/W2979157532","https://openalex.org/W3015584015","https://openalex.org/W3017343282","https://openalex.org/W3046890131","https://openalex.org/W3103837916","https://openalex.org/W3108240585","https://openalex.org/W3110013267","https://openalex.org/W4289665794","https://openalex.org/W6685352114","https://openalex.org/W6736723571","https://openalex.org/W6743737169","https://openalex.org/W6745560452","https://openalex.org/W6747045456","https://openalex.org/W6748048626","https://openalex.org/W6749767719","https://openalex.org/W6750298367","https://openalex.org/W6750591037","https://openalex.org/W6750651883","https://openalex.org/W6755257315","https://openalex.org/W6758675244","https://openalex.org/W6776264637","https://openalex.org/W6780316881","https://openalex.org/W6780770960","https://openalex.org/W6781756758"],"related_works":["https://openalex.org/W3160582690","https://openalex.org/W353528578","https://openalex.org/W2968808972","https://openalex.org/W3198586259","https://openalex.org/W2908965201","https://openalex.org/W3161635175","https://openalex.org/W2785892019","https://openalex.org/W2188568971","https://openalex.org/W3023271457","https://openalex.org/W3096936389","https://openalex.org/W2783457476","https://openalex.org/W2963715927","https://openalex.org/W2996158613","https://openalex.org/W2945439681","https://openalex.org/W2997685131","https://openalex.org/W2770520232","https://openalex.org/W2963828546","https://openalex.org/W3203164940","https://openalex.org/W34233450","https://openalex.org/W3110936599"],"abstract_inverted_index":{"There":[0],"have":[1,8],"been":[2,51],"a":[3,19,58,109],"number":[4],"of":[5,12,38,41,70,80],"techniques":[6],"that":[7,60,62,93,116],"demonstrated":[9],"the":[10,25,36,76,94,98],"generation":[11,40,79],"multimedia":[13],"data":[14,74],"for":[15,44,111],"one":[16],"modality":[17],"at":[18],"time":[20],"using":[21,128],"GANs,":[22],"such":[23,132],"as":[24,133],"ability":[26],"to":[27,66,91,120],"generate":[28,67,121],"images,":[29],"videos,":[30],"and":[31,46,72,82,97,114,140],"audio.":[32],"However,":[33],"so":[34],"far,":[35],"task":[37,113],"multi-modal":[39],"data,":[42],"specifically":[43],"audio":[45,73,81],"videos":[47],"both,":[48],"has":[49],"not":[50],"sufficiently":[52],"well-explored.":[53],"Towards":[54],"this,":[55],"we":[56,63,117],"propose":[57],"method":[59,87,125],"demonstrates":[61],"are":[64,101,118],"able":[65,119],"naturalistic":[68],"samples":[69],"video":[71,83],"by":[75],"joint":[77,99],"correlated":[78],"modalities.":[84],"The":[85],"proposed":[86],"uses":[88],"multiple":[89],"discriminators":[90],"ensure":[92],"audio,":[95],"video,":[96],"output":[100],"also":[102],"indistinguishable":[103],"from":[104],"real-world":[105],"samples.":[106,123],"We":[107],"present":[108],"dataset":[110],"this":[112],"show":[115],"realistic":[122],"This":[124],"is":[126],"validated":[127],"various":[129],"standard":[130],"metrics":[131],"Inception":[134,137],"Score,":[135],"Frechet":[136],"Distance":[138],"(FID)":[139],"through":[141],"human":[142],"evaluation.":[143]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
