{"id":"https://openalex.org/W2737697117","doi":"https://doi.org/10.1145/3072959.3073702","title":"VoCo","display_name":"VoCo","publication_year":2017,"publication_date":"2017-07-20","ids":{"openalex":"https://openalex.org/W2737697117","doi":"https://doi.org/10.1145/3072959.3073702","mag":"2737697117"},"language":"en","primary_location":{"id":"doi:10.1145/3072959.3073702","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3072959.3073702","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-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/A5100702050","display_name":"Zeyu Jin","orcid":"https://orcid.org/0000-0003-0161-5915"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Jin","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044614923","display_name":"Gautham J. Mysore","orcid":"https://orcid.org/0000-0003-0483-9252"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gautham J. Mysore","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036534746","display_name":"Stephen DiVerdi","orcid":"https://orcid.org/0000-0002-6694-3381"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen Diverdi","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085050428","display_name":"Jingwan Lu","orcid":"https://orcid.org/0000-0002-3598-9918"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingwan Lu","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034842939","display_name":"Adam Finkelstein","orcid":"https://orcid.org/0000-0001-9422-5363"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Finkelstein","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.8457,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.96969697,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"36","issue":"4","first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9997000098228455,"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/T11439","display_name":"Video Analysis and Summarization","score":0.998199999332428,"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":0.8308423757553101},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6844440698623657},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6360177993774414},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5841808319091797},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.5216891169548035},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5091637969017029},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5007193088531494},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.500307559967041},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.4959958493709564},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.42150601744651794},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36827945709228516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29783201217651367},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19949617981910706},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11697572469711304}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8308423757553101},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6844440698623657},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6360177993774414},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5841808319091797},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.5216891169548035},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5091637969017029},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5007193088531494},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.500307559967041},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.4959958493709564},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.42150601744651794},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36827945709228516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29783201217651367},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19949617981910706},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11697572469711304},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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:10.1145/3072959.3073702","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3072959.3073702","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":112,"referenced_works":["https://openalex.org/W11019033","https://openalex.org/W59175527","https://openalex.org/W95152782","https://openalex.org/W146976060","https://openalex.org/W153299664","https://openalex.org/W176245312","https://openalex.org/W178225857","https://openalex.org/W946300668","https://openalex.org/W1497428175","https://openalex.org/W1499332833","https://openalex.org/W1499821160","https://openalex.org/W1505932402","https://openalex.org/W1514889585","https://openalex.org/W1517202054","https://openalex.org/W1523998723","https://openalex.org/W1530162522","https://openalex.org/W1542833741","https://openalex.org/W1544407768","https://openalex.org/W1549473933","https://openalex.org/W1570629387","https://openalex.org/W1599623585","https://openalex.org/W1600722501","https://openalex.org/W1637570796","https://openalex.org/W1741199358","https://openalex.org/W1834627372","https://openalex.org/W1875231349","https://openalex.org/W1902237438","https://openalex.org/W1956880900","https://openalex.org/W1964202597","https://openalex.org/W1965912016","https://openalex.org/W1978806573","https://openalex.org/W1980618402","https://openalex.org/W1997240284","https://openalex.org/W2000931629","https://openalex.org/W2007023536","https://openalex.org/W2027419931","https://openalex.org/W2035046981","https://openalex.org/W2039800941","https://openalex.org/W2049686551","https://openalex.org/W2051903221","https://openalex.org/W2058653743","https://openalex.org/W2058733260","https://openalex.org/W2060666149","https://openalex.org/W2061171222","https://openalex.org/W2082388554","https://openalex.org/W2086796102","https://openalex.org/W2091425152","https://openalex.org/W2100649345","https://openalex.org/W2102003408","https://openalex.org/W2103868465","https://openalex.org/W2107860279","https://openalex.org/W2111284386","https://openalex.org/W2119695540","https://openalex.org/W2120605154","https://openalex.org/W2121095010","https://openalex.org/W2123003832","https://openalex.org/W2126143605","https://openalex.org/W2129142580","https://openalex.org/W2130942839","https://openalex.org/W2131062138","https://openalex.org/W2136166660","https://openalex.org/W2137575240","https://openalex.org/W2141708418","https://openalex.org/W2142384583","https://openalex.org/W2145892079","https://openalex.org/W2147152002","https://openalex.org/W2147885303","https://openalex.org/W2150658333","https://openalex.org/W2152974894","https://openalex.org/W2153914468","https://openalex.org/W2154920538","https://openalex.org/W2155498861","https://openalex.org/W2156142001","https://openalex.org/W2160379050","https://openalex.org/W2251498782","https://openalex.org/W2259800260","https://openalex.org/W2267632979","https://openalex.org/W2292976057","https://openalex.org/W2296422624","https://openalex.org/W2296704011","https://openalex.org/W2328165521","https://openalex.org/W2394921947","https://openalex.org/W2395718496","https://openalex.org/W2402356521","https://openalex.org/W2406990556","https://openalex.org/W2408467190","https://openalex.org/W2423557781","https://openalex.org/W2518172956","https://openalex.org/W2559246505","https://openalex.org/W2591927543","https://openalex.org/W2604184139","https://openalex.org/W2654729393","https://openalex.org/W2746474733","https://openalex.org/W2747914378","https://openalex.org/W2749651610","https://openalex.org/W2769810959","https://openalex.org/W2777302760","https://openalex.org/W2890983311","https://openalex.org/W2891355459","https://openalex.org/W2891813127","https://openalex.org/W2901997113","https://openalex.org/W2949382160","https://openalex.org/W2951535099","https://openalex.org/W2963035245","https://openalex.org/W2963192573","https://openalex.org/W2963712897","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W3123895079","https://openalex.org/W3142087749","https://openalex.org/W4214544731","https://openalex.org/W6650376485"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W2348886128","https://openalex.org/W2388067091","https://openalex.org/W2367656648","https://openalex.org/W2350200549","https://openalex.org/W2362132076","https://openalex.org/W2965396777","https://openalex.org/W2012262991","https://openalex.org/W2389168924","https://openalex.org/W2067294484"],"abstract_inverted_index":{"Editing":[0],"audio":[1],"narration":[2],"using":[3],"conventional":[4],"software":[5],"typically":[6],"involves":[7],"many":[8],"painstaking":[9],"low-level":[10],"manipulations.":[11],"Some":[12],"state":[13],"of":[14,27,109,134,174,176,192,219],"the":[15,19,28,40,49,60,64,73,94,99,107,110,132,135,150,169,179,207,217,231],"art":[16],"systems":[17],"allow":[18],"editor":[20],"to":[21,48,66,97,141,145,148,161,178],"work":[22],"in":[23,39,51,59,72,102,131,152],"a":[24,52,78,85,103,115,120,143,153,165,172,189],"text":[25,144],"transcript":[26],"narration,":[29],"and":[30,35,156,200,203,227],"perform":[31],"select,":[32],"cut,":[33],"copy":[34],"paste":[36],"operations":[37,43],"directly":[38],"transcript;":[41],"these":[42],"are":[44],"then":[45,157],"automatically":[46],"applied":[47],"waveform":[50],"straightforward":[53],"manner.":[54],"However,":[55],"an":[56],"obvious":[57],"gap":[58],"text-based":[61],"interface":[62,182],"is":[63,96,140,222],"ability":[65],"type":[67],"new":[68,79,100,121],"words":[69],"not":[70],"appearing":[71],"transcript,":[74],"for":[75,81],"example":[76],"inserting":[77],"word":[80,101,122,151],"emphasis":[82],"or":[83,123],"replacing":[84],"misspoken":[86],"word.":[87],"While":[88],"high-quality":[89],"voice":[90,104,159,166],"synthesizers":[91],"exist":[92],"today,":[93],"challenge":[95],"synthesize":[98,119],"that":[105,117,127,167,216],"matches":[106,168],"rest":[108],"narration.":[111,137,170],"This":[112],"paper":[113,212],"presents":[114,213],"system":[116],"can":[118],"short":[124],"phrase":[125],"such":[126],"it":[128,163],"blends":[129],"seamlessly":[130],"context":[133],"existing":[136],"Our":[138],"approach":[139],"use":[142,158],"speech":[146],"synthesizer":[147],"say":[149],"generic":[154],"voice,":[155],"conversion":[160],"convert":[162],"into":[164],"Offering":[171],"range":[173],"degrees":[175],"control":[177,196],"editor,":[180],"our":[181,220],"supports":[183],"fully":[184],"automatic":[185],"synthesis,":[186],"selection":[187],"among":[188],"candidate":[190],"set":[191],"alternative":[193],"pronunciations,":[194],"fine":[195],"over":[197,224],"edit":[198],"placements":[199],"pitch":[201],"profiles,":[202],"even":[204],"guidance":[205],"by":[206],"editors":[208],"own":[209],"voice.":[210,233],"The":[211],"studies":[214],"showing":[215],"output":[218],"method":[221],"preferred":[223],"baseline":[225],"methods":[226],"often":[228],"indistinguishable":[229],"from":[230],"original":[232]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2017-07-31T00:00:00"}