{"id":"https://openalex.org/W3092611012","doi":"https://doi.org/10.1109/icassp39728.2021.9413488","title":"Audio-Visual Speech Inpainting with Deep Learning","display_name":"Audio-Visual Speech Inpainting with Deep Learning","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3092611012","doi":"https://doi.org/10.1109/icassp39728.2021.9413488","mag":"3092611012"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413488","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.04556","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040930642","display_name":"Giovanni Morrone","orcid":"https://orcid.org/0000-0003-2163-1779"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]},{"id":"https://openalex.org/I4210161797","display_name":"Ferrari (Italy)","ror":"https://ror.org/05p859a12","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210161797"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Morrone","raw_affiliation_strings":["University of Modena and Reggio Emilia,Department of Engineering \"Enzo Ferrari\",Italy","University of Modena and Reggio Emilia, Department of Engineering \u201cEnzo Ferrari\u201d, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia,Department of Engineering \"Enzo Ferrari\",Italy","institution_ids":["https://openalex.org/I122346577","https://openalex.org/I4210161797"]},{"raw_affiliation_string":"University of Modena and Reggio Emilia, Department of Engineering \u201cEnzo Ferrari\u201d, Italy","institution_ids":["https://openalex.org/I122346577","https://openalex.org/I4210161797"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063187524","display_name":"Daniel Michelsanti","orcid":"https://orcid.org/0000-0002-3575-1600"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Daniel Michelsanti","raw_affiliation_strings":["Aalborg University,Department of Electronic Systems,Denmark","Aalborg University, Dept. of Electronic Systems, Denmark#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Department of Electronic Systems,Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Aalborg University, Dept. of Electronic Systems, Denmark#TAB#","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":["Aalborg University,Department of Electronic Systems,Denmark","Aalborg University, Dept. of Electronic Systems, Denmark#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Department of Electronic Systems,Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Aalborg University, Dept. of Electronic Systems, Denmark#TAB#","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101679595","display_name":"Jesper Jensen","orcid":"https://orcid.org/0000-0003-1478-622X"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jesper Jensen","raw_affiliation_strings":["Aalborg University,Department of Electronic Systems,Denmark","Aalborg University, Dept. of Electronic Systems, Denmark#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Department of Electronic Systems,Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Aalborg University, Dept. of Electronic Systems, Denmark#TAB#","institution_ids":["https://openalex.org/I891191580"]}]}],"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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6653","last_page":"6657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.8968164920806885},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.74217689037323},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7353515028953552},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6210656762123108},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5557886362075806},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.47120922803878784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4564298987388611},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.21218785643577576},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06477141380310059}],"concepts":[{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.8968164920806885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.74217689037323},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7353515028953552},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6210656762123108},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5557886362075806},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47120922803878784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4564298987388611},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.21218785643577576},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06477141380310059},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413488","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:2010.04556","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.04556","pdf_url":"https://arxiv.org/pdf/2010.04556","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":"","raw_type":null},{"id":"mag:3092611012","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.04556.pdf","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":"pmh:oai:iris.unimore.it:11380/1220454","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.04556v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.atira.dk:publications/8b8907e8-5059-4edd-8d36-49b662543c0a","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/8b8907e8-5059-4edd-8d36-49b662543c0a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"contributionToPeriodical"},{"id":"doi:10.48550/arxiv.2010.04556","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.04556","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":"Preprint"},{"id":"doi:10.17023/721g-4c56","is_oa":true,"landing_page_url":"https://doi.org/10.17023/721g-4c56","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"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":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.04556","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.04556","pdf_url":"https://arxiv.org/pdf/2010.04556","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":"","raw_type":null},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1552314771","https://openalex.org/W1635512741","https://openalex.org/W1828163288","https://openalex.org/W2015143272","https://openalex.org/W2110027626","https://openalex.org/W2111727455","https://openalex.org/W2127141656","https://openalex.org/W2141998673","https://openalex.org/W2143612262","https://openalex.org/W2147585306","https://openalex.org/W2161304220","https://openalex.org/W2296153915","https://openalex.org/W2556910157","https://openalex.org/W2741913599","https://openalex.org/W2755891984","https://openalex.org/W2898371500","https://openalex.org/W2900292050","https://openalex.org/W2913340405","https://openalex.org/W2963276790","https://openalex.org/W2964121744","https://openalex.org/W2981283774","https://openalex.org/W2981905048","https://openalex.org/W2985518820","https://openalex.org/W2999894541","https://openalex.org/W3012382391","https://openalex.org/W3015252514","https://openalex.org/W3015526955","https://openalex.org/W3022195800","https://openalex.org/W3096650361","https://openalex.org/W3105183525","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6744261651","https://openalex.org/W6769995984","https://openalex.org/W6772649462","https://openalex.org/W6775691539","https://openalex.org/W6782486312"],"related_works":["https://openalex.org/W3161904430","https://openalex.org/W2997382144","https://openalex.org/W2577762507","https://openalex.org/W3004146833","https://openalex.org/W2797032258","https://openalex.org/W3015445830","https://openalex.org/W1520113716","https://openalex.org/W3169721356","https://openalex.org/W2288334518","https://openalex.org/W2102149658","https://openalex.org/W3182657421","https://openalex.org/W2116497041","https://openalex.org/W1608493013","https://openalex.org/W2208724044","https://openalex.org/W2134764753","https://openalex.org/W2735610159","https://openalex.org/W3201437620","https://openalex.org/W2888868298","https://openalex.org/W1503808328","https://openalex.org/W2396163457"],"abstract_inverted_index":{"In":[0,128],"this":[1],"paper,":[2],"we":[3,55,130],"present":[4],"a":[5,85,90],"deep-learning-based":[6],"framework":[7],"for":[8,76],"audio-visual":[9,119],"speech":[10,23,57,98,107],"inpainting,":[11],"i.e.,":[12],"the":[13,17,70,103,117,138],"task":[14,93],"of":[15,20,78,105],"restoring":[16],"missing":[18,126],"parts":[19],"an":[21],"acoustic":[22],"signal":[24],"from":[25,62,144],"reliable":[26],"audio":[27],"context":[28],"and":[29,40],"uncorrupted":[30],"visual":[31],"information.":[32,127],"Recent":[33],"work":[34],"focuses":[35],"solely":[36],"on":[37],"audio-only":[38,106],"methods":[39],"generally":[41],"aims":[42],"at":[43],"inpainting":[44,108],"music":[45],"signals,":[46],"which":[47],"show":[48,101,131],"highly":[49],"different":[50,79],"structure":[51],"than":[52],"speech.":[53],"Instead,":[54],"inpaint":[56],"signals":[58],"with":[59,84,97],"gaps":[60,77,113],"ranging":[61],"100":[63],"ms":[64,67],"to":[65,68,123,141],"1600":[66],"investigate":[69],"contribution":[71,140],"that":[72,102,132],"vision":[73],"can":[74],"provide":[75],"duration.":[80],"We":[81],"also":[82],"experiment":[83],"multi-task":[86,133],"learning":[87,134],"approach":[88,120],"where":[89],"phone":[91],"recognition":[92],"is":[94,121,135],"learned":[95],"together":[96],"inpainting.":[99],"Results":[100],"performance":[104,142],"approaches":[109],"degrades":[110],"rapidly":[111],"when":[112],"get":[114],"large,":[115],"while":[116],"proposed":[118],"able":[122],"plausibly":[124],"restore":[125],"addition,":[129],"effective,":[136],"although":[137],"largest":[139],"comes":[143],"vision.":[145]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}