{"id":"https://openalex.org/W3117141796","doi":"https://doi.org/10.1145/3395035.3425640","title":"See me Speaking? Differentiating on Whether Words are Spoken On Screen or Off to Optimize Machine Dubbing","display_name":"See me Speaking? Differentiating on Whether Words are Spoken On Screen or Off to Optimize Machine Dubbing","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3117141796","doi":"https://doi.org/10.1145/3395035.3425640","mag":"3117141796"},"language":"en","primary_location":{"id":"doi:10.1145/3395035.3425640","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3395035.3425640","pdf_url":null,"source":{"id":"https://openalex.org/S4306506653","display_name":"Companion Publication of the 2020 International Conference on Multimodal Interaction","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":"Companion Publication of the 2020 International Conference on Multimodal Interaction","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/A5003441670","display_name":"Shravan Nayak","orcid":"https://orcid.org/0000-0002-5298-7121"},"institutions":[{"id":"https://openalex.org/I56404289","display_name":"Indian Institute of Technology BHU","ror":"https://ror.org/01kh5gc44","country_code":"IN","type":"education","lineage":["https://openalex.org/I56404289"]},{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Shravan Nayak","raw_affiliation_strings":["Indian Institute of Technology (BHU), Varanasi, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology (BHU), Varanasi, India","institution_ids":["https://openalex.org/I56404289","https://openalex.org/I91357014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087628586","display_name":"Timo Baumann","orcid":"https://orcid.org/0000-0003-2203-1783"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Timo Baumann","raw_affiliation_strings":["Universit\u00e4t Hamburg, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Universit\u00e4t Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112743835","display_name":"Supratik Bhattacharya","orcid":null},"institutions":[{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Supratik Bhattacharya","raw_affiliation_strings":["Birla Institute of Technology and Science, Pilani, India"],"affiliations":[{"raw_affiliation_string":"Birla Institute of Technology and Science, Pilani, India","institution_ids":["https://openalex.org/I74796645"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047533259","display_name":"Alina Karakanta","orcid":"https://orcid.org/0000-0002-1029-1337"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]},{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alina Karakanta","raw_affiliation_strings":["Fondazione Bruno Kessler &amp; University of Trento, Trento, Italy"],"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler &amp; University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I2277624104","https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015363344","display_name":"Matteo Negri","orcid":"https://orcid.org/0000-0002-8811-4330"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Matteo Negri","raw_affiliation_strings":["Fondazione Bruno Kessler, Trento, Italy"],"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler, Trento, Italy","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025827839","display_name":"Marco Turchi","orcid":"https://orcid.org/0000-0002-5899-4496"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Turchi","raw_affiliation_strings":["Fondazione Bruno Kessler, Trento, Italy"],"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler, Trento, Italy","institution_ids":["https://openalex.org/I2277624104"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5003441670"],"corresponding_institution_ids":["https://openalex.org/I56404289","https://openalex.org/I91357014"],"apc_list":null,"apc_paid":null,"fwci":7.1934,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.96997691,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"130","last_page":"134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9962999820709229,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9940999746322632,"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":0.7686180472373962},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6010763645172119},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.47282537817955017},{"id":"https://openalex.org/keywords/cognitive-dissonance","display_name":"Cognitive dissonance","score":0.47117120027542114},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4686196446418762},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.46380046010017395},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4303250312805176},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.390780508518219},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36111676692962646},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2799261510372162},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1665991246700287}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7686180472373962},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6010763645172119},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.47282537817955017},{"id":"https://openalex.org/C77513098","wikidata":"https://www.wikidata.org/wiki/Q209722","display_name":"Cognitive dissonance","level":2,"score":0.47117120027542114},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4686196446418762},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.46380046010017395},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4303250312805176},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.390780508518219},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36111676692962646},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2799261510372162},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1665991246700287},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3395035.3425640","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3395035.3425640","pdf_url":null,"source":{"id":"https://openalex.org/S4306506653","display_name":"Companion Publication of the 2020 International Conference on Multimodal Interaction","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":"Companion Publication of the 2020 International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W267812377","https://openalex.org/W561433424","https://openalex.org/W1509966554","https://openalex.org/W1628791547","https://openalex.org/W1718330812","https://openalex.org/W1902237438","https://openalex.org/W2341528187","https://openalex.org/W2605182378","https://openalex.org/W2610617489","https://openalex.org/W2807126412","https://openalex.org/W2901647871","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W2970971581","https://openalex.org/W2971345947","https://openalex.org/W3016098309","https://openalex.org/W3101998545","https://openalex.org/W4232998634"],"related_works":["https://openalex.org/W3208334015","https://openalex.org/W2767403522","https://openalex.org/W2258133373","https://openalex.org/W2766249179","https://openalex.org/W2255937062","https://openalex.org/W1974328274","https://openalex.org/W1515826403","https://openalex.org/W4310034585","https://openalex.org/W1509473192","https://openalex.org/W2296205523"],"abstract_inverted_index":{"Dubbing":[0],"is":[1,42],"the":[2,24,35,45,74,84,87,129,152],"art":[3],"of":[4,48,60,119,142,154],"finding":[5],"a":[6,9,12,116,140],"translation":[7,85],"from":[8,135],"source":[10],"into":[11],"target":[13,25],"language":[14,26],"that":[15,22,146],"can":[16],"be":[17],"lip-synchronously":[18],"revoiced,":[19],"i.":[20],"e.,":[21],"makes":[23],"speech":[27,120,137],"appear":[28],"as":[29,53,57],"if":[30],"it":[31],"was":[32],"spoken":[33],"by":[34],"very":[36],"actors":[37],"all":[38],"along.":[39],"Lip":[40],"synchrony":[41,61,79,99],"essential":[43],"for":[44,105,115,128,151],"full-fledged":[46],"reception":[47],"foreign":[49],"audiovisual":[50],"media,":[51],"such":[52],"movies":[54],"and":[55,65,72],"series,":[56],"violated":[58],"constraints":[59,80,100],"between":[62],"video":[63],"(lips)":[64],"audio":[66],"(speech)":[67],"lead":[68],"to":[69,83,97,132],"cognitive":[70],"dissonance":[71],"reduce":[73],"perceptual":[75],"quality.":[76],"Of":[77],"course,":[78],"only":[81],"apply":[82,98],"when":[86],"speaker's":[88],"lips":[89,110,156],"are":[90,111],"visible":[91,112],"on":[92,113,139,157],"screen.":[93,158],"Therefore,":[94],"deciding":[95],"whether":[96,107],"requires":[101],"an":[102,108],"automatic":[103],"method":[104],"detecting":[106],"actor's":[109],"screen":[114],"given":[117],"stretch":[118],"or":[121],"not.":[122],"In":[123],"this":[124],"paper,":[125],"we":[126,165],"attempt,":[127],"first":[130],"time,":[131],"classify":[133,166],"on-":[134],"off-screen":[136],"based":[138],"corpus":[141],"real-world":[143],"television":[144],"material":[145],"has":[147],"been":[148],"annotated":[149],"word-by-word":[150],"visibility":[153],"talking":[155],"We":[159],"present":[160],"classification":[161],"experiments":[162],"in":[163],"which":[164]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
