{"id":"https://openalex.org/W4225956675","doi":"https://doi.org/10.21437/interspeech.2022-439","title":"UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022","display_name":"UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4225956675","doi":"https://doi.org/10.21437/interspeech.2022-439"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-439","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-439","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/A5025983709","display_name":"Takaaki Saeki","orcid":"https://orcid.org/0000-0001-6003-768X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takaaki Saeki","raw_affiliation_strings":["The University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072398606","display_name":"Detai Xin","orcid":"https://orcid.org/0009-0007-1908-1137"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Detai Xin","raw_affiliation_strings":["The University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098356112","display_name":"Wataru Nakata","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wataru Nakata","raw_affiliation_strings":["The University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024181978","display_name":"Tomoki Koriyama","orcid":"https://orcid.org/0000-0002-8347-5604"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Koriyama","raw_affiliation_strings":["The University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinnosuke Takamichi","raw_affiliation_strings":["The University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["The University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5025983709"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":15.6783,"has_fulltext":false,"cited_by_count":207,"citation_normalized_percentile":{"value":0.99491121,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4521","last_page":"4525"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9987000226974487,"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/T11309","display_name":"Music and Audio Processing","score":0.9807999730110168,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9616000056266785,"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":0.6151359677314758}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6151359677314758}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-439","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-439","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":[{"display_name":"Quality Education","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1406023492","display_name":null,"funder_award_id":"21H04900","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3480867415","display_name":null,"funder_award_id":"JPMJPS2011","funder_id":"https://openalex.org/F4320338247","funder_display_name":"Moonshot Research and Development Program"},{"id":"https://openalex.org/G3752857035","display_name":null,"funder_award_id":"JPMJSP2108","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8199958842","display_name":"Speech Processing Based on Deep Gaussian Process With Stochastic Differential Equation Layers","funder_award_id":"21K11955","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338247","display_name":"Moonshot Research and Development Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W28412257","https://openalex.org/W70888257","https://openalex.org/W605727707","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1673310716","https://openalex.org/W2557915412","https://openalex.org/W2768348081","https://openalex.org/W2962897394","https://openalex.org/W2972394484","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3090098535","https://openalex.org/W3144810982","https://openalex.org/W3160506022","https://openalex.org/W3161558238","https://openalex.org/W3169320628","https://openalex.org/W3196225973","https://openalex.org/W3198429080","https://openalex.org/W3200245256","https://openalex.org/W3202278141","https://openalex.org/W3209984917","https://openalex.org/W4300816538","https://openalex.org/W4311829866","https://openalex.org/W4322714819"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"We":[0],"present":[1],"the":[2,19,75,97,102,110,122],"UTokyo-SaruLab":[3],"mean":[4],"opinion":[5],"score":[6,104],"(MOS)":[7],"prediction":[8,42],"system":[9,59,100],"submitted":[10],"to":[11,17,74,91,120],"VoiceMOS":[12],"Challenge":[13],"2022.The":[14],"challenge":[15],"is":[16,51,60],"predict":[18,92],"MOS":[20],"values":[21],"of":[22,65,79,124],"speech":[23],"samples":[24],"collected":[25],"from":[26,55,94],"previous":[27,76],"Blizzard":[28],"Challenges":[29,33],"and":[30,43,67,112],"Voice":[31],"Conversion":[32],"for":[34,40,48,108],"two":[35],"tracks:":[36],"a":[37],"main":[38,111],"track":[39,47],"in-domain":[41],"an":[44],"out-of-domain":[45],"(OOD)":[46],"which":[49],"there":[50],"less":[52],"labeled":[53],"data":[54],"different":[56],"listening":[57],"tests.Our":[58],"based":[61],"on":[62,105],"ensemble":[63],"learning":[64,81],"strong":[66],"weak":[68,85],"learners.Strong":[69],"learners":[70,86],"incorporate":[71],"several":[72,106],"improvements":[73],"finetuning":[77],"models":[78],"self-supervised":[80],"(SSL)":[82],"models,":[83],"while":[84],"use":[87],"basic":[88],"machine-learning":[89],"methods":[90],"scores":[93],"SSL":[95],"features.In":[96],"Challenge,":[98],"our":[99,125],"had":[101],"highest":[103],"metrics":[107],"both":[109],"OOD":[113],"tracks.In":[114],"addition,":[115],"we":[116],"conducted":[117],"ablation":[118],"studies":[119],"investigate":[121],"effectiveness":[123],"proposed":[126],"methods.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":56},{"year":2025,"cited_by_count":98},{"year":2024,"cited_by_count":34},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-03T09:05:47.796612","created_date":"2025-10-10T00:00:00"}