{"id":"https://openalex.org/W4206204999","doi":"https://doi.org/10.23919/eusipco54536.2021.9616266","title":"Speaker disentanglement in video-to-speech conversion","display_name":"Speaker disentanglement in video-to-speech conversion","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W4206204999","doi":"https://doi.org/10.23919/eusipco54536.2021.9616266"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616266","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616266","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013389452","display_name":"Dan Onea\u0163\u0103","orcid":"https://orcid.org/0000-0003-4354-4393"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Dan Oneata","raw_affiliation_strings":["University Politehnica of Bucharest, Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"University Politehnica of Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018126799","display_name":"Adriana Stan","orcid":"https://orcid.org/0000-0003-2894-5770"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Adriana Stan","raw_affiliation_strings":["Technical University of Cluj-Napoca, Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032257745","display_name":"Horia Cucu","orcid":"https://orcid.org/0000-0002-8711-3854"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Horia Cucu","raw_affiliation_strings":["University Politehnica of Bucharest, Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"University Politehnica of Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013389452"],"corresponding_institution_ids":["https://openalex.org/I61641377"],"apc_list":null,"apc_paid":null,"fwci":1.3763,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.88784419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"46","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9843000173568726,"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":0.756621241569519},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6368062496185303}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.756621241569519},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6368062496185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616266","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616266","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.46000000834465027,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G8504410743","display_name":null,"funder_award_id":"PN-III-P1-1.1-PD-2019-0918","funder_id":"https://openalex.org/F4320308292","funder_display_name":"Corporation for National and Community Service"}],"funders":[{"id":"https://openalex.org/F4320308292","display_name":"Corporation for National and Community Service","ror":"https://ror.org/00p8rjs69"},{"id":"https://openalex.org/F4320324070","display_name":"Ministry of Education and Research, Romania","ror":"https://ror.org/00dh5gw98"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1882958252","https://openalex.org/W2015143272","https://openalex.org/W2068056889","https://openalex.org/W2194775991","https://openalex.org/W2251321385","https://openalex.org/W2293856338","https://openalex.org/W2402146185","https://openalex.org/W2584505851","https://openalex.org/W2585824449","https://openalex.org/W2619368999","https://openalex.org/W2767052532","https://openalex.org/W2808706139","https://openalex.org/W2887437849","https://openalex.org/W2907262790","https://openalex.org/W2916104401","https://openalex.org/W2963010714","https://openalex.org/W2964243274","https://openalex.org/W2964283370","https://openalex.org/W2964352155","https://openalex.org/W2964404767","https://openalex.org/W2971905065","https://openalex.org/W2972563022","https://openalex.org/W3024559545","https://openalex.org/W3035626590","https://openalex.org/W3101481642","https://openalex.org/W6639480849","https://openalex.org/W6691770337","https://openalex.org/W6732945439","https://openalex.org/W6745317255","https://openalex.org/W6746173266","https://openalex.org/W6746700228","https://openalex.org/W6752888775","https://openalex.org/W6757660528","https://openalex.org/W6760057544","https://openalex.org/W6765987481","https://openalex.org/W6768158615"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"The":[0],"task":[1,21],"of":[2,9,28,77,112,117,126,154,171,190],"video-to-speech":[3,72],"aims":[4],"to":[5,12,19,25,45,80,163],"translate":[6],"silent":[7],"video":[8,149],"lip":[10,124],"movement":[11],"its":[13],"corresponding":[14],"audio":[15],"signal.":[16],"Previous":[17],"approaches":[18],"this":[20,66],"are":[22],"generally":[23],"limited":[24],"the":[26,81,86,109,113,119,123,127,133,145,148,152,157,161,172,183,188,191],"case":[27],"a":[29,33,70,98,102],"single":[30],"speaker,":[31],"but":[32],"method":[34,159],"that":[35,108,143],"accounts":[36],"for":[37,179],"multiple":[38,50],"speakers":[39,51],"is":[40,115,160],"desirable":[41],"as":[42,168],"it":[43,79],"allows":[44],"(i)":[46,169],"leverage":[47],"datasets":[48],"with":[49,88],"or":[52,101],"few":[53],"samples":[54],"per":[55],"speaker;":[56],"and":[57,74,137,175],"(ii)":[58,176],"control":[59,170],"speaker":[60,103,120,138],"identity":[61,100,121,146],"at":[62],"inference":[63],"time.":[64],"In":[65],"paper,":[67],"we":[68,84,95,106],"introduce":[69],"new":[71],"architecture":[73],"explore":[75],"ways":[76],"extending":[78],"multi-speaker":[82],"scenario:":[83],"augment":[85],"network":[87,114],"an":[89],"additional":[90],"speaker-related":[91],"input,":[92],"through":[93],"which":[94],"feed":[96],"either":[97],"discrete":[99],"embedding.":[104],"Interestingly,":[105],"observe":[107],"visual":[110],"encoder":[111],"capable":[116],"learning":[118],"from":[122,147],"region":[125],"face":[128],"alone.":[129],"To":[130,151],"better":[131],"disentangle":[132],"two":[134],"inputs-linguistic":[135],"content":[136],"identity-we":[139],"add":[140],"adversarial":[141],"losses":[142],"dispel":[144],"embeddings.":[150],"best":[153],"our":[155],"knowledge,":[156],"proposed":[158],"first":[162],"provide":[164],"important":[165],"functionalities":[166],"such":[167],"target":[173],"voice":[174],"speech":[177],"synthesis":[178],"unseen":[180],"identities":[181],"over":[182],"state-of-the-art,":[184],"while":[185],"still":[186],"maintaining":[187],"intelligibility":[189],"spoken":[192],"output.":[193]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
