{"id":"https://openalex.org/W3196225973","doi":"https://doi.org/10.21437/ssw.2021-32","title":"How do Voices from Past Speech Synthesis Challenges Compare Today?","display_name":"How do Voices from Past Speech Synthesis Challenges Compare Today?","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3196225973","doi":"https://doi.org/10.21437/ssw.2021-32","mag":"3196225973"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2021-32","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-32","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","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/A5082349516","display_name":"Erica Cooper","orcid":"https://orcid.org/0000-0002-2978-2793"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Erica Cooper","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082349516"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.8019,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.94352101,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"183","last_page":"188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962000250816345,"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":0.9962000250816345,"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/T10028","display_name":"Topic Modeling","score":0.9517999887466431,"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/T12031","display_name":"Speech and dialogue systems","score":0.9498999714851379,"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/active-listening","display_name":"Active listening","score":0.7915088534355164},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7352137565612793},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.7123032808303833},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.5227767825126648},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4992055892944336},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.486625999212265},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44929495453834534},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42420023679733276},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40210434794425964},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3722667098045349},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33649733662605286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2752879858016968},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11241039633750916}],"concepts":[{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.7915088534355164},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7352137565612793},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.7123032808303833},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.5227767825126648},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4992055892944336},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.486625999212265},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44929495453834534},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42420023679733276},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40210434794425964},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3722667098045349},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33649733662605286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2752879858016968},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11241039633750916},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/ssw.2021-32","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-32","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W2997121352","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W4237969969","https://openalex.org/W1594297642","https://openalex.org/W2366328218"],"abstract_inverted_index":{"Shared":[0],"challenges":[1,44,80,91],"provide":[2,19],"a":[3,13,63,83,102,120,124],"venue":[4],"for":[5,23,45,49,133],"comparing":[6],"systems":[7,106],"trained":[8],"on":[9,166],"common":[10],"data":[11,27],"using":[12],"standardized":[14],"evaluation,":[15],"and":[16,28,37,48,53,58,81,98,111,117,130,151],"they":[17],"also":[18,157],"an":[20],"invaluable":[21],"resource":[22],"researchers":[24],"when":[25],"the":[26,71,144,148,159,162],"evaluation":[29],"results":[30,61,150],"are":[31,41,95],"publicly":[32],"released.":[33],"The":[34],"Blizzard":[35],"Challenge":[36,40],"Voice":[38],"Conversion":[39],"two":[42],"such":[43],"text-to-speech":[46],"synthesis":[47,68,167],"speaker":[50,165],"conversion,":[51],"respectively,":[52],"their":[54,131],"publicly-available":[55],"system":[56,145],"samples":[57,88,129],"listening":[59,85,154],"test":[60,86],"comprise":[62],"historical":[64],"record":[65],"of":[66,101,105,123,127,161,164],"state-of-the-art":[67],"methods":[69],"over":[70,115],"years.":[72],"In":[73],"this":[74],"paper,":[75],"we":[76],"revisit":[77],"these":[78],"past":[79],"conduct":[82],"large-scale":[84,121],"with":[87],"from":[89],"many":[90],"combined.":[92],"Our":[93],"aims":[94],"to":[96,108,118],"analyze":[97],"compare":[99],"opinions":[100,113],"large":[103],"number":[104],"together,":[107],"determine":[109],"whether":[110],"how":[112],"change":[114],"time,":[116],"collect":[119],"dataset":[122],"diverse":[125],"variety":[126],"synthetic":[128],"ratings":[132],"further":[134],"research.":[135],"We":[136,156],"found":[137],"strong":[138],"correlations":[139],"challenge":[140,142],"by":[141],"at":[143],"level":[146],"between":[147],"original":[149],"our":[152],"new":[153],"test.":[155],"observed":[158],"importance":[160],"choice":[163],"quality.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
