{"id":"https://openalex.org/W4390451904","doi":"https://doi.org/10.1145/3611380.3628562","title":"KyotoMOS: An Automatic MOS Scoring System for Speech Synthesis","display_name":"KyotoMOS: An Automatic MOS Scoring System for Speech Synthesis","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4390451904","doi":"https://doi.org/10.1145/3611380.3628562"},"language":"en","primary_location":{"id":"doi:10.1145/3611380.3628562","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3611380.3628562","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3611380.3628562","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia Workshops","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3611380.3628562","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032740716","display_name":"Wangjin Zhou","orcid":"https://orcid.org/0009-0007-0693-5316"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Wangjin Zhou","raw_affiliation_strings":["Kyoto University, JP"],"affiliations":[{"raw_affiliation_string":"Kyoto University, JP","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005468171","display_name":"Zhengdong Yang","orcid":"https://orcid.org/0009-0003-1629-3266"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhengdong Yang","raw_affiliation_strings":["Kyoto University, JP"],"affiliations":[{"raw_affiliation_string":"Kyoto University, JP","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["National Institute of Information and Communications Technology (NICT), JP"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT), JP","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102757632","display_name":"Chenhui Chu","orcid":"https://orcid.org/0000-0001-9848-6384"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chenhui Chu","raw_affiliation_strings":["Kyoto University, JP"],"affiliations":[{"raw_affiliation_string":"Kyoto University, JP","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5032740716"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":0.3442,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6809461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"7","issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.996999979019165,"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":0.996999979019165,"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":0.9912999868392944,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9616000056266785,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.799822211265564},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7962062358856201},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.7459272146224976},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5912259221076965},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5447618961334229},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5249999761581421},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.49483054876327515},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.47687989473342896},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46965494751930237},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39646974205970764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36143630743026733},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20750373601913452},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1767306923866272},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08879557251930237},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.08566856384277344},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.06922543048858643}],"concepts":[{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.799822211265564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7962062358856201},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.7459272146224976},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5912259221076965},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5447618961334229},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.49483054876327515},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.47687989473342896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46965494751930237},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39646974205970764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36143630743026733},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20750373601913452},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1767306923866272},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08879557251930237},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.08566856384277344},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.06922543048858643},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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":3,"locations":[{"id":"doi:10.1145/3611380.3628562","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3611380.3628562","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3611380.3628562","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia Workshops","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01221:0006026429","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/286919","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"MMAsia'23 Workshops: Proceedings of the 5th ACM International Conference on Multimedia in Asia Workshops","raw_type":"conference paper"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50729883","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100931487","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.1145/3611380.3628562","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3611380.3628562","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3611380.3628562","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia Workshops","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1069223013","display_name":null,"funder_award_id":"JSPS KAKENHI","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3459562248","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4390204761","display_name":null,"funder_award_id":"JP23K11227","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4636223006","display_name":null,"funder_award_id":"JSPS KAK","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4778811342","display_name":"\u502b\u7406\u3068\u8a00\u8a9e\u3068\u306e\u76f8\u4e92\u95a2\u4fc2\u306b\u3064\u3044\u3066","funder_award_id":"11227","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4827429566","display_name":null,"funder_award_id":"Grant Numbers","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8430481527","display_name":null,"funder_award_id":"Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8471687183","display_name":"M3OLR: Towards Effective Multilingual, Multimodal and Multitask Oriental Low-resourced Language Speech Recognition","funder_award_id":"23K11227","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390451904.pdf","grobid_xml":"https://content.openalex.org/works/W4390451904.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2592497314","https://openalex.org/W4223503417","https://openalex.org/W4387427365"],"related_works":["https://openalex.org/W2618286804","https://openalex.org/W2329643025","https://openalex.org/W2002770077","https://openalex.org/W3131163342","https://openalex.org/W2092256833","https://openalex.org/W2142369114","https://openalex.org/W2361728394","https://openalex.org/W2166271660","https://openalex.org/W3089582840","https://openalex.org/W3081644756"],"abstract_inverted_index":{"The":[0],"Mean":[1],"Opinion":[2],"Score":[3],"(MOS)":[4],"serves":[5],"as":[6,60],"a":[7,71],"subjective":[8],"measure":[9],"for":[10,52,76,82],"assessing":[11],"the":[12,18,49,66],"quality":[13],"of":[14,29,65],"synthesized":[15],"speech.":[16],"Nevertheless,":[17],"conventional":[19],"approach":[20],"to":[21],"MOS":[22,39,73],"evaluations":[23],"can":[24],"be":[25],"resource-intensive":[26],"in":[27,47,55,62],"terms":[28],"both":[30],"time":[31],"and":[32,58,78,88],"cost.":[33],"This":[34],"article":[35],"unveils":[36],"an":[37],"automatic":[38],"scoring":[40,74],"toolkit":[41],"that":[42],"builds":[43],"upon":[44],"our":[45],"success":[46],"securing":[48],"top":[50],"position":[51],"some":[53,63],"metrics":[54],"VoiceMos2022":[56],"Challenge":[57],"emerging":[59],"champions":[61],"tracks":[64],"VoiceMos2023":[67],"Challenge.":[68],"We":[69],"offer":[70],"pre-trained":[72],"tool":[75],"English":[77],"provide":[79],"training":[80],"code":[81,90],"other":[83],"languages.":[84],"Our":[85],"documentation,":[86],"examples,":[87],"source":[89],"are":[91],"available":[92],"at":[93],"https://github.com/superphysics/KyotoMOS.":[94]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}
