{"id":"https://openalex.org/W4401609230","doi":"https://doi.org/10.1109/icasspw62465.2024.10626267","title":"Uncertainty as a Predictor: Leveraging Self-Supervised Learning for Zero-Shot MOS Prediction","display_name":"Uncertainty as a Predictor: Leveraging Self-Supervised Learning for Zero-Shot MOS Prediction","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401609230","doi":"https://doi.org/10.1109/icasspw62465.2024.10626267"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10626267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10626267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5023289998","display_name":"Aditya Ravuri","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Aditya Ravuri","raw_affiliation_strings":["University of Cambridge,Cambridge,UK"],"affiliations":[{"raw_affiliation_string":"University of Cambridge,Cambridge,UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","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,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Tokyo,Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"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,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Tokyo,Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023289998"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":2.3109,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88470915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"580","last_page":"584"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.9042999744415283,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.9042999744415283,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5938048362731934},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5264708995819092},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5207671523094177},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.46761760115623474},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4666796922683716},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.11847350001335144}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5938048362731934},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5264708995819092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5207671523094177},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.46761760115623474},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4666796922683716},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.11847350001335144},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10626267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10626267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W582134693","https://openalex.org/W2138204974","https://openalex.org/W2531327146","https://openalex.org/W2933138175","https://openalex.org/W2973049979","https://openalex.org/W3036601975","https://openalex.org/W3179485843","https://openalex.org/W3198270377","https://openalex.org/W3208743843","https://openalex.org/W4226380987","https://openalex.org/W4283694096","https://openalex.org/W4296068974","https://openalex.org/W4296070386","https://openalex.org/W4322714819","https://openalex.org/W4366342913","https://openalex.org/W4372260534","https://openalex.org/W4391021560","https://openalex.org/W4391021755","https://openalex.org/W6617145748","https://openalex.org/W6680106237","https://openalex.org/W6728622933","https://openalex.org/W6780218876","https://openalex.org/W6798272402","https://openalex.org/W6839364956","https://openalex.org/W6851400169"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Predicting":[0],"audio":[1,37,116],"quality":[2,38,117],"in":[3,35,41,107,133],"voice":[4],"synthesis":[5],"and":[6,84,98],"conversion":[7],"systems":[8],"is":[9],"a":[10],"critical":[11],"yet":[12],"challenging":[13],"task,":[14],"especially":[15,40],"when":[16],"traditional":[17],"methods":[18],"like":[19],"Mean":[20],"Opinion":[21],"Scores":[22],"(MOS)":[23],"are":[24,77,129],"cumbersome":[25],"to":[26],"collect":[27],"at":[28],"scale.":[29],"This":[30],"paper":[31],"addresses":[32],"the":[33,82,90,124,130],"gap":[34],"efficient":[36],"prediction,":[39],"low-resource":[42],"settings":[43],"where":[44],"extensive":[45],"MOS":[46,73],"data":[47,80],"from":[48,61,81],"large-scale":[49],"listening":[50],"tests":[51],"may":[52],"be":[53],"unavailable.":[54],"We":[55,88],"demonstrate":[56],"that":[57,123],"uncertainty":[58],"measures":[59],"derived":[60],"out-of-the-box":[62],"pre-trained":[63],"self-supervised":[64],"learning":[65],"(SSL)":[66],"models,":[67],"such":[68],"as":[69,112],"wav2vec,":[70],"correlate":[71],"with":[72],"scores.":[74],"These":[75],"findings":[76],"based":[78],"on":[79],"2022":[83],"2023":[85],"VoiceMOS":[86],"challenges.":[87],"explore":[89],"extent":[91],"of":[92],"this":[93],"correlation":[94],"across":[95],"different":[96],"models":[97,109,128],"language":[99],"contexts,":[100],"revealing":[101],"insights":[102],"into":[103],"how":[104],"inherent":[105],"uncertainties":[106],"SSL":[108],"can":[110],"serve":[111],"effective":[113],"proxies":[114],"for":[115],"assessment.":[118],"In":[119],"particular,":[120],"we":[121],"show":[122],"contrastive":[125],"wav2vec":[126],"(1.0)":[127],"most":[131],"performant":[132],"all":[134],"settings.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}