{"id":"https://openalex.org/W4226019720","doi":"https://doi.org/10.21437/interspeech.2022-970","title":"The VoiceMOS Challenge 2022","display_name":"The VoiceMOS Challenge 2022","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4226019720","doi":"https://doi.org/10.21437/interspeech.2022-970"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-970","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-970","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.11389","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000377034","display_name":"Wen-Chin Huang","orcid":"https://orcid.org/0000-0003-3172-3335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen Chin Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082349516","display_name":"Erica Cooper","orcid":"https://orcid.org/0000-0002-2978-2793"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erica Cooper","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057697869","display_name":"Tao Yu","orcid":"https://orcid.org/0000-0002-0143-261X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":[],"raw_orcid":null,"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":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4536","last_page":"4540"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7734000086784363,"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":0.7734000086784363,"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/T10863","display_name":"Voice and Speech Disorders","score":0.04580000042915344,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.03280000016093254,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.7306268811225891},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6639711856842041},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6433058381080627},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6231918931007385},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5622076988220215},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.5394917130470276},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5117273330688477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45439910888671875},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45319923758506775},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.45029565691947937},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39498651027679443},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23785001039505005},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10736104846000671},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.08164265751838684},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07597306370735168}],"concepts":[{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.7306268811225891},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6639711856842041},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6433058381080627},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6231918931007385},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5622076988220215},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.5394917130470276},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5117273330688477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45439910888671875},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45319923758506775},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.45029565691947937},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39498651027679443},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23785001039505005},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10736104846000671},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.08164265751838684},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07597306370735168},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2022-970","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-970","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"},{"id":"pmh:oai:arXiv.org:2203.11389","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.11389","pdf_url":"https://arxiv.org/pdf/2203.11389","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2203.11389","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.11389","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.11389","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.11389","pdf_url":"https://arxiv.org/pdf/2203.11389","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W868042","https://openalex.org/W354571","https://openalex.org/W149980","https://openalex.org/W592020","https://openalex.org/W4883666","https://openalex.org/W1614943","https://openalex.org/W9950073","https://openalex.org/W10050918","https://openalex.org/W17058891","https://openalex.org/W4781179"],"abstract_inverted_index":{"We":[0],"present":[1],"the":[2,6,16,22,48,62,66,86,104,107,115,122,138],"first":[3],"edition":[4],"of":[5,18,21,27,44,50,54,65,69,83,90,103,109,124],"VoiceMOS":[7],"Challenge,":[8],"a":[9,42,81,98],"scientific":[10],"event":[11],"that":[12],"aims":[13],"to":[14,46],"promote":[15],"study":[17],"automatic":[19],"prediction":[20,117],"mean":[23],"opinion":[24],"score":[25],"(MOS)":[26],"synthetic":[28],"speech.":[29,56],"This":[30],"challenge":[31,67,105],"drew":[32],"22":[33],"participating":[34],"teams":[35],"from":[36,71,92],"academia":[37],"and":[38,75,85,131,133],"industry":[39],"who":[40],"tried":[41],"variety":[43],"approaches":[45],"tackle":[47],"problem":[49],"predicting":[51,125],"human":[52],"ratings":[53,127],"synthesized":[55],"The":[57],"listening":[58,100],"test":[59],"data":[60,91],"for":[61,114,128,134],"main":[63],"track":[64,88],"consisted":[68,89],"samples":[70],"187":[72],"different":[73],"text-to-speech":[74],"voice":[76],"conversion":[77],"systems":[78,95,136],"spanning":[79],"over":[80],"decade":[82],"research,":[84],"out-of-domain":[87,139],"more":[93],"recent":[94],"rated":[96],"in":[97,137],"separate":[99],"test.":[101],"Results":[102],"show":[106],"effectiveness":[108],"fine-tuning":[110],"self-supervised":[111],"speech":[112],"models":[113],"MOS":[116,126],"task,":[118],"as":[119,121],"well":[120],"difficulty":[123],"unseen":[129,135],"speakers":[130],"listeners,":[132],"setting.":[140]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-05-05T00:00:00"}