{"id":"https://openalex.org/W4385823134","doi":"https://doi.org/10.21437/interspeech.2023-1020","title":"Speech inpainting: Context-based speech synthesis guided by video","display_name":"Speech inpainting: Context-based speech synthesis guided by video","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823134","doi":"https://doi.org/10.21437/interspeech.2023-1020"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1020","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repositori.upf.edu/bitstreams/dec7639a-78f8-4b01-b34f-7275d3baae08/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055470699","display_name":"Juan F. Montesinos","orcid":"https://orcid.org/0000-0002-1373-3639"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juan Felipe Montesinos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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/I4210130492","display_name":"Oticon Medical (Denmark)","ror":"https://ror.org/03c5ds320","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210130492"]},{"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":["Oticon Danmark AS, DK","Aalborg University, The Technical Faculty of IT and Design, DK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oticon Danmark AS, DK","institution_ids":["https://openalex.org/I4210130492"]},{"raw_affiliation_string":"Aalborg University, The Technical Faculty of IT and Design, DK","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077048730","display_name":"Gloria Haro","orcid":"https://orcid.org/0000-0002-8194-8092"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gloria Haro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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, The Technical Faculty of IT and Design, DK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University, The Technical Faculty of IT and Design, DK","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/I4210130492","display_name":"Oticon Medical (Denmark)","ror":"https://ror.org/03c5ds320","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210130492"]},{"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":["Oticon Danmark AS, DK","Aalborg University, The Technical Faculty of IT and Design, DK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oticon Danmark AS, DK","institution_ids":["https://openalex.org/I4210130492"]},{"raw_affiliation_string":"Aalborg University, The Technical Faculty of IT and Design, DK","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4459","last_page":"4463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9818999767303467,"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":0.9818999767303467,"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/T11448","display_name":"Face recognition and analysis","score":0.9751999974250793,"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/T12290","display_name":"Human Motion and Animation","score":0.9598000049591064,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7805513143539429},{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.7716457843780518},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6641647815704346},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6376404762268066},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5816361308097839},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5059353709220886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4300643801689148},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2032308578491211},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.04929381608963013}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7805513143539429},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.7716457843780518},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6641647815704346},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6376404762268066},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5816361308097839},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5059353709220886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4300643801689148},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2032308578491211},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.04929381608963013},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2023-1020","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:repositori-api.upf.edu:10230/70023","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/70023","pdf_url":"https://repositori.upf.edu/bitstreams/dec7639a-78f8-4b01-b34f-7275d3baae08/download","source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.atira.dk:publications/5dd63539-2ab7-4b1b-9db8-773821ffc186","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/5dd63539-2ab7-4b1b-9db8-773821ffc186","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":"Montesinos, J F, Michelsanti, D, Haro, G, Tan, Z H & Jensen, J 2023, Speech inpainting : Context-based speech synthesis guided by video. in Proc. INTERSPEECH 2023. ISCA, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, pp. 4459-4463, 24th International Speech Communication Association, Interspeech 2023, Dublin, Ireland, 20/08/2023. https://doi.org/10.21437/Interspeech.2023-1020","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:repositori-api.upf.edu:10230/70023","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/70023","pdf_url":"https://repositori.upf.edu/bitstreams/dec7639a-78f8-4b01-b34f-7275d3baae08/download","source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385823134.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2380775572","https://openalex.org/W2213520135","https://openalex.org/W2244018504","https://openalex.org/W4242046654","https://openalex.org/W3174923100","https://openalex.org/W3134074939","https://openalex.org/W2117562399","https://openalex.org/W4298074124","https://openalex.org/W2587407424","https://openalex.org/W1523707610"],"abstract_inverted_index":{"Audio":[0],"and":[1,12,76,110],"visual":[2,26,74,91,117],"modalities":[3],"are":[4,15,129],"inherently":[5],"connected":[6],"in":[7,59,64],"speech":[8,18,32,49,58,127],"signals:":[9],"lip":[10],"movements":[11],"facial":[13],"expressions":[14],"correlated":[16],"with":[17,71,120],"sounds.":[19],"This":[20],"motivates":[21],"studies":[22],"that":[23,67,89,93],"incorporate":[24],"the":[25,45,53,57,72,77,97,100,105],"modality":[27],"to":[28],"enhance":[29],"an":[30,83],"acoustic":[31],"signal":[33],"or":[34],"even":[35],"restore":[36],"missing":[37],"audio":[38,62,79],"information.":[39],"Specifically,":[40],"this":[41],"paper":[42],"focuses":[43],"on":[44],"problem":[46],"of":[47,55,99],"audio-visual":[48,84,108],"inpainting,":[50],"which":[51],"is":[52,69],"task":[54],"synthesizing":[56,132],"a":[60,65,122],"corrupted":[61,101],"segment":[63],"way":[66],"it":[68],"consistent":[70],"corresponding":[73],"content":[75,98],"uncorrupted":[78],"context.":[80],"We":[81,113],"present":[82],"transformer-based":[85],"deep":[86],"learning":[87],"model":[88,109],"leverages":[90],"cues":[92],"provide":[94],"information":[95],"about":[96],"audio.":[102],"It":[103],"outperforms":[104],"previous":[106],"state-of-the-art":[107],"audio-only":[111],"baselines.":[112],"also":[114],"show":[115],"how":[116],"features":[118],"extracted":[119],"AV-HuBERT,":[121],"large":[123],"audiovisual":[124],"transformer":[125],"for":[126,131],"recognition,":[128],"suitable":[130],"speech.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2023-08-15T00:00:00"}
