{"id":"https://openalex.org/W4406461503","doi":"https://doi.org/10.1109/slt61566.2024.10832295","title":"The Voicemos Challenge 2024: Beyond Speech Quality Prediction","display_name":"The Voicemos Challenge 2024: Beyond Speech Quality Prediction","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461503","doi":"https://doi.org/10.1109/slt61566.2024.10832295"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/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":true,"raw_author_name":"Wen-Chin Huang","raw_affiliation_strings":["Nagoya University,Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071471469","display_name":"Szu\u2010Wei Fu","orcid":"https://orcid.org/0000-0002-3487-8212"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Szu-Wei Fu","raw_affiliation_strings":["NVIDIA,Taiwan"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Taiwan","institution_ids":[]}]},{"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/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":"Erica Cooper","raw_affiliation_strings":["National Institute Of Information And Communications Technology,Japan"],"affiliations":[{"raw_affiliation_string":"National Institute Of Information And Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030281426","display_name":"Ryandhimas E. Zezario","orcid":"https://orcid.org/0000-0001-7319-8263"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ryandhimas E. Zezario","raw_affiliation_strings":["Academia Sinica,Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Academia Sinica,Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","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"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Academia Sinica,Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5000377034"],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":5.1829,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.96491228,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"803","last_page":"810"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.6561381816864014},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6051174402236938},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5792332887649536},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4108313024044037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3495488166809082},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.052548497915267944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6561381816864014},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6051174402236938},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5792332887649536},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4108313024044037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3495488166809082},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.052548497915267944},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2052666245","https://openalex.org/W2593116425","https://openalex.org/W2603567530","https://openalex.org/W2973133192","https://openalex.org/W3026777299","https://openalex.org/W3097906045","https://openalex.org/W3097945073","https://openalex.org/W3161480375","https://openalex.org/W3181854487","https://openalex.org/W3196225973","https://openalex.org/W3198429080","https://openalex.org/W3202278141","https://openalex.org/W3207932315","https://openalex.org/W3209984917","https://openalex.org/W4221143458","https://openalex.org/W4221144124","https://openalex.org/W4225302959","https://openalex.org/W4226403810","https://openalex.org/W4253928870","https://openalex.org/W4296068974","https://openalex.org/W4297570641","https://openalex.org/W4311167834","https://openalex.org/W4372260534","https://openalex.org/W4383961998","https://openalex.org/W4385807442","https://openalex.org/W4385822628","https://openalex.org/W4385823334","https://openalex.org/W4386304689","https://openalex.org/W4387941762","https://openalex.org/W4391021560","https://openalex.org/W4391021724","https://openalex.org/W4391421598","https://openalex.org/W4393859250","https://openalex.org/W4399794707","https://openalex.org/W4401609230","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6793164127","https://openalex.org/W6838724896","https://openalex.org/W6847363464","https://openalex.org/W6861531434","https://openalex.org/W6861858043","https://openalex.org/W6869945801"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"We":[0],"present":[1],"the":[2,6,33,93,109,118,132,136],"third":[3,69],"edition":[4],"of":[5,19,35,50,63,86,120,138],"VoiceMOS":[7],"Challenge,":[8],"a":[9,60,82],"scientific":[10],"initiative":[11],"designed":[12],"to":[13,47,107],"advance":[14],"research":[15],"into":[16],"automatic":[17],"prediction":[18,74],"human":[20],"speech":[21,40,140],"ratings.":[22],"There":[23],"were":[24,105],"three":[25],"tracks.":[26],"The":[27,43,68],"first":[28],"track":[29,45,70],"was":[30,46,71,90],"on":[31],"predicting":[32],"quality":[34,73],"\u201czoomed-in\u201d":[36],"high-quality":[37],"samples":[38,51],"from":[39,52,96],"synthesis":[41,55],"systems.":[42,111],"second":[44],"predict":[48],"ratings":[49],"singing":[53],"voice":[54,57],"and":[56,66,78,99,117,125],"conversion":[58],"with":[59],"large":[61],"variety":[62],"systems,":[64],"listeners,":[65],"languages.":[67],"semi-supervised":[72],"for":[75],"noisy,":[76],"clean,":[77],"enhanced":[79],"speech,":[80],"where":[81],"very":[83],"small":[84],"amount":[85],"labeled":[87],"training":[88],"data":[89],"provided.":[91],"Among":[92],"eight":[94],"teams":[95],"both":[97],"academia":[98],"industry,":[100],"we":[101],"found":[102],"that":[103,131],"many":[104],"able":[106],"outperform":[108],"baseline":[110],"Successful":[112],"techniques":[113],"included":[114],"retrieval-based":[115],"methods":[116],"use":[119],"non-self-supervised":[121],"representations":[122],"like":[123],"spectrograms":[124],"pitch":[126],"histograms.":[127],"These":[128],"results":[129],"showed":[130],"challenge":[133],"has":[134],"advanced":[135],"field":[137],"subjective":[139],"rating":[141],"prediction.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
