{"id":"https://openalex.org/W4296070449","doi":"https://doi.org/10.21437/interspeech.2022-11136","title":"Isochrony-Aware Neural Machine Translation for Automatic Dubbing","display_name":"Isochrony-Aware Neural Machine Translation for Automatic Dubbing","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296070449","doi":"https://doi.org/10.21437/interspeech.2022-11136"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11136","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11136","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5112879125","display_name":"Derek Tam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Derek Tam","raw_affiliation_strings":["AWS AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010634671","display_name":"Surafel M. Lakew","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Surafel M. Lakew","raw_affiliation_strings":["AWS AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110544572","display_name":"Yogesh Virkar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yogesh Virkar","raw_affiliation_strings":["AWS AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057049978","display_name":"Prashant Mathur","orcid":"https://orcid.org/0000-0002-9271-1373"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prashant Mathur","raw_affiliation_strings":["AWS AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110629070","display_name":"Marcello Federico","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcello Federico","raw_affiliation_strings":["AWS AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5309,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.75005324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1776","last_page":"1780"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9713000059127808,"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"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9713000059127808,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9375,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7180066108703613},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6317766904830933},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4819352626800537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42594262957572937},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.389590322971344},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38438284397125244},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06401365995407104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7180066108703613},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6317766904830933},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4819352626800537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42594262957572937},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.389590322971344},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38438284397125244},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06401365995407104},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11136","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11136","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2250342921","https://openalex.org/W2737638662","https://openalex.org/W2786991584","https://openalex.org/W2901647871","https://openalex.org/W2941599692","https://openalex.org/W2963225662","https://openalex.org/W2963876447","https://openalex.org/W2970780025","https://openalex.org/W2971345947","https://openalex.org/W2972425358","https://openalex.org/W2980145022","https://openalex.org/W2982026991","https://openalex.org/W3037752342","https://openalex.org/W3037838322","https://openalex.org/W3037915423","https://openalex.org/W3084396630","https://openalex.org/W3092085609","https://openalex.org/W3158927431","https://openalex.org/W3161049737","https://openalex.org/W3176048559","https://openalex.org/W4225302758","https://openalex.org/W4297756269","https://openalex.org/W4297824597","https://openalex.org/W4385245566","https://openalex.org/W4392352873"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W2775554247","https://openalex.org/W2883671469","https://openalex.org/W2110168585","https://openalex.org/W3107474891","https://openalex.org/W2250213760","https://openalex.org/W4386247111","https://openalex.org/W4327642362","https://openalex.org/W2587014613","https://openalex.org/W3204019825"],"abstract_inverted_index":{"We":[0],"introduce":[1],"the":[2,22,27,31,34,47,50,60,64,95,98],"task":[3],"of":[4,16,30,63,97,108],"isochrony-aware":[5],"machine":[6,84],"translation":[7],"which":[8],"aims":[9],"at":[10],"generating":[11],"translations":[12,109],"suitable":[13],"for":[14],"dubbing.Dubbing":[15],"a":[17],"spoken":[18],"sentence":[19],"requires":[20],"transferring":[21],"content":[23],"as":[24,26],"well":[25],"speech-pause":[28],"structure":[29],"source":[32,48,66],"into":[33,82],"target":[35,51,55],"language":[36,88],"to":[37,49,78],"achieve":[38],"audiovisual":[39],"coherence.Practically,":[40],"this":[41,69],"implies":[42],"correctly":[43],"projecting":[44],"pauses":[45],"from":[46],"and":[52,74,110],"ensuring":[53],"that":[54,94],"speech":[56,67],"segments":[57],"have":[58],"roughly":[59],"same":[61],"duration":[62],"corresponding":[65],"segments.In":[68],"work,":[70],"we":[71],"propose":[72],"implicit":[73],"explicit":[75],"modeling":[76],"approaches":[77,100],"integrate":[79],"isochrony":[80],"information":[81],"neural":[83],"translation.Experiments":[85],"on":[86],"English-German/French":[87],"pairs":[89],"with":[90],"automatic":[91],"metrics":[92],"show":[93],"simplest":[96],"considered":[99],"works":[101],"best.Results":[102],"are":[103],"confirmed":[104],"by":[105],"human":[106],"evaluations":[107],"dubbed":[111],"videos.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}