{"id":"https://openalex.org/W3202278141","doi":"https://doi.org/10.1109/icassp43922.2022.9746395","title":"Generalization Ability of MOS Prediction Networks","display_name":"Generalization Ability of MOS Prediction Networks","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3202278141","doi":"https://doi.org/10.1109/icassp43922.2022.9746395","mag":"3202278141"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746395","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746395","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Erica Cooper","raw_affiliation_strings":["National Institute of Informatics,Japan","National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000377034","display_name":"Wen-Chin Huang","orcid":"https://orcid.org/0000-0003-3172-3335"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wen-Chin Huang","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics,Japan","National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":135,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8442","last_page":"8446"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9976000189781189,"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/T11309","display_name":"Music and Audio Processing","score":0.9940000176429749,"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/computer-science","display_name":"Computer science","score":0.7642899751663208},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7448756694793701},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6511313319206238},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5748746991157532},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5331271290779114},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4876028597354889},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4805160462856293},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.4767116904258728},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46443021297454834},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.42940250039100647},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10589659214019775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7642899751663208},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7448756694793701},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6511313319206238},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5748746991157532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5331271290779114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4876028597354889},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4805160462856293},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.4767116904258728},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46443021297454834},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42940250039100647},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10589659214019775},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"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/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746395","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746395","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6600000262260437}],"awards":[{"id":"https://openalex.org/G749109276","display_name":"Can AI Rakugoka entertain people? -Improved expressiveness of rakugo speech synthesis and automatic generation of storytelling","funder_award_id":"21K19808","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W1494198834","https://openalex.org/W2119929864","https://openalex.org/W2166637769","https://openalex.org/W2394921947","https://openalex.org/W2473388484","https://openalex.org/W2515028311","https://openalex.org/W2796495654","https://openalex.org/W2915960560","https://openalex.org/W2917245127","https://openalex.org/W2917438849","https://openalex.org/W2917688842","https://openalex.org/W2936802426","https://openalex.org/W2962780374","https://openalex.org/W2963035245","https://openalex.org/W2963522141","https://openalex.org/W2967606780","https://openalex.org/W2972394484","https://openalex.org/W2995181338","https://openalex.org/W3016160783","https://openalex.org/W3024752295","https://openalex.org/W3026777299","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3082130377","https://openalex.org/W3083776549","https://openalex.org/W3095410713","https://openalex.org/W3099782249","https://openalex.org/W3161558238","https://openalex.org/W3169320628","https://openalex.org/W3196225973","https://openalex.org/W3197580070","https://openalex.org/W3198270377","https://openalex.org/W3209059054","https://openalex.org/W4395699642","https://openalex.org/W4395699666","https://openalex.org/W4395958010","https://openalex.org/W4395958177","https://openalex.org/W6603931906","https://openalex.org/W6712208827","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6865107258","https://openalex.org/W6865530009"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W3177678247","https://openalex.org/W2174706483","https://openalex.org/W2997121352","https://openalex.org/W419536403"],"abstract_inverted_index":{"Automatic":[0],"methods":[1],"to":[2,33,60,63,117,136],"predict":[3],"listener":[4],"opinions":[5],"of":[6,17,74,126],"synthesized":[7],"speech":[8,83],"remain":[9],"elusive":[10],"since":[11],"listeners,":[12],"systems":[13,147],"being":[14],"evaluated,":[15],"characteristics":[16],"the":[18,22,26,54,122,130],"speech,":[19],"and":[20,25,81,101,133],"even":[21,120],"instructions":[23],"given":[24],"rating":[27],"scale":[28],"all":[29],"vary":[30],"from":[31,53,94],"test":[32,66],"test.":[34],"While":[35],"automatic":[36],"predictors":[37],"for":[38,76,110,121,151],"metrics":[39],"such":[40,85],"as":[41,86],"mean":[42],"opinion":[43],"score":[44],"(MOS)":[45],"can":[46,139],"achieve":[47],"high":[48],"prediction":[49,78,112,153],"accuracy":[50],"on":[51,92],"samples":[52],"same":[55],"test,":[56],"they":[57],"typically":[58],"fail":[59],"generalize":[61],"well":[62],"new":[64],"listening":[65,96],"contexts.":[67],"In":[68],"this":[69],"paper,":[70],"using":[71],"a":[72],"variety":[73],"networks":[75],"MOS":[77,111,152],"including":[79],"MOSNet":[80],"self-supervised":[82],"models":[84,108],"wav2vec2,":[87],"we":[88],"investigate":[89],"their":[90],"performance":[91],"data":[93,119,138],"different":[95],"tests":[97],"in":[98,129],"both":[99],"zero-shot":[100,131],"fine-tuned":[102,109],"settings.":[103],"We":[104,142],"find":[105],"that":[106,134,145],"wav2vec2":[107],"have":[113],"good":[114],"generalization":[115],"capability":[116],"out-of-domain":[118],"most":[123],"challenging":[124,150],"case":[125],"utterance-level":[127],"predictions":[128],"setting,":[132],"fine-tuning":[135],"in-domain":[137],"improve":[140],"predictions.":[141],"also":[143],"observe":[144],"unseen":[146],"are":[148],"especially":[149],"models.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":42},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":39},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}