{"id":"https://openalex.org/W4283819462","doi":"https://doi.org/10.1109/ncc55593.2022.9806799","title":"Subtitle Synthesis using Inter and Intra utterance Prosodic Alignment for Automatic Dubbing","display_name":"Subtitle Synthesis using Inter and Intra utterance Prosodic Alignment for Automatic Dubbing","publication_year":2022,"publication_date":"2022-05-24","ids":{"openalex":"https://openalex.org/W4283819462","doi":"https://doi.org/10.1109/ncc55593.2022.9806799"},"language":"en","primary_location":{"id":"doi:10.1109/ncc55593.2022.9806799","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc55593.2022.9806799","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 National Conference on Communications (NCC)","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/A5065642629","display_name":"Giridhar Pamisetty","orcid":"https://orcid.org/0000-0001-5945-6860"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Giridhar Pamisetty","raw_affiliation_strings":["Indian Institute of Technology Hyderabad,Department of Electrical Engineering,Hyderabad,India","Department of Electrical Engineering, Indian Institute of Technology Hyderabad, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Hyderabad,Department of Electrical Engineering,Hyderabad,India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":null,"display_name":"Sri Rama Murty Kodukula","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sri Rama Murty Kodukula","raw_affiliation_strings":["Indian Institute of Technology Hyderabad,Department of Electrical Engineering,Hyderabad,India","Department of Electrical Engineering, Indian Institute of Technology Hyderabad, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Hyderabad,Department of Electrical Engineering,Hyderabad,India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065642629"],"corresponding_institution_ids":["https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06604532,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs 2110 2854","issue":null,"first_page":"250","last_page":"255"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9979000091552734,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9979000091552734,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9937999844551086,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9936000108718872,"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/speech-synthesis","display_name":"Speech synthesis","score":0.8394883871078491},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8386688232421875},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7843325734138489},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7685792446136475},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7593564987182617},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6619612574577332},{"id":"https://openalex.org/keywords/subtitle","display_name":"Subtitle","score":0.6054384708404541},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5698098540306091},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5379121899604797},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4665833115577698},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.45438018441200256},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.4413710832595825},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3728269338607788},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3465588092803955},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11932504177093506},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09193560481071472},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08009913563728333},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06616142392158508}],"concepts":[{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.8394883871078491},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8386688232421875},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7843325734138489},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7685792446136475},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7593564987182617},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6619612574577332},{"id":"https://openalex.org/C2780364048","wikidata":"https://www.wikidata.org/wiki/Q204028","display_name":"Subtitle","level":2,"score":0.6054384708404541},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5698098540306091},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5379121899604797},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4665833115577698},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.45438018441200256},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.4413710832595825},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3728269338607788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3465588092803955},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11932504177093506},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09193560481071472},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08009913563728333},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06616142392158508},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ncc55593.2022.9806799","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc55593.2022.9806799","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 National Conference on Communications (NCC)","raw_type":"proceedings-article"},{"id":"pmh:oai:raiith.iith.ac.in:10063","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400292","display_name":"Research Archive of Indian Institute of Technology Hyderabad (Indian Institute of Technology Hyderabad)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I65181880","host_organization_name":"Indian Institute of Technology Hyderabad","host_organization_lineage":["https://openalex.org/I65181880"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W23643102","https://openalex.org/W1522301498","https://openalex.org/W2018338387","https://openalex.org/W2094069964","https://openalex.org/W2103478679","https://openalex.org/W2104029973","https://openalex.org/W2147144097","https://openalex.org/W2471520273","https://openalex.org/W2972425358","https://openalex.org/W3037838322","https://openalex.org/W3084396630","https://openalex.org/W3158927431","https://openalex.org/W3161049737","https://openalex.org/W3176048559","https://openalex.org/W3203313352","https://openalex.org/W6631190155","https://openalex.org/W6682004709","https://openalex.org/W6795075085","https://openalex.org/W6801828018"],"related_works":["https://openalex.org/W169399214","https://openalex.org/W258725851","https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W2108985546","https://openalex.org/W2081919107"],"abstract_inverted_index":{"Automatic":[0],"dubbing":[1,4],"or":[2],"machine":[3],"is":[5,22],"the":[6,10,13,17,36,39,49,56,61,75,81,85,89,95,98,110,119,122,128,135,138,144,149,153,157,170,176,193,196],"process":[7],"of":[8,48,97,121,159,175,189,195],"replacing":[9],"speech":[11,32,58],"in":[12,38,109,183],"source":[14,40,139],"video":[15,41],"with":[16,35],"desired":[18],"language":[19],"speech,":[20,150],"which":[21,151],"synthesized":[23,31,57,99,136],"using":[24],"a":[25,44,71,184],"text-to-speech":[26],"synthesis":[27],"(TTS)":[28],"system.":[29],"The":[30,172],"should":[33,115],"align":[34],"events":[37],"to":[42,124,131,147,155],"have":[43,116],"realistic":[45],"experience.":[46],"Most":[47],"existing":[50],"prosodic":[51,76,86,111,198],"alignment":[52,77,108,112,126,199],"processes":[53],"operate":[54],"on":[55],"by":[59],"controlling":[60],"speaking":[62],"rate.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,142],"propose":[68],"subtitle":[69],"synthesis,":[70],"unified":[72],"approach":[73],"for":[74],"that":[78,191],"operates":[79],"at":[80,88,127],"feature":[82,90,129],"level.":[83],"Modifying":[84],"parameters":[87],"level":[91,130],"will":[92],"not":[93],"degrade":[94],"naturalness":[96],"speech.":[100,140],"We":[101,114],"use":[102,143],"both":[103],"inter":[104],"and":[105,137,161],"intra":[106],"utterance":[107],"process.":[113,200],"control":[117,156],"over":[118],"duration":[120,158],"phonemes":[123,160],"perform":[125],"achieve":[132],"synchronization":[133],"between":[134],"So,":[141],"Prosody-TTS":[145],"system":[146],"synthesize":[148],"has":[152],"provision":[154],"fundamental":[162],"frequency":[163],"(f":[164],"<inf":[165],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[166],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0</inf>":[167],")":[168],"during":[169],"synthesis.":[171],"subjective":[173],"evaluation":[174],"translated":[177],"audiovisual":[178],"content":[179],"(lecture":[180],"videos)":[181],"resulted":[182],"mean":[185],"opinion":[186],"score":[187],"(MOS)":[188],"4.104":[190],"indicates":[192],"effectiveness":[194],"proposed":[197]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
