{"id":"https://openalex.org/W4406461865","doi":"https://doi.org/10.1109/slt61566.2024.10832315","title":"The T05 System for the voicemos challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech","display_name":"The T05 System for the voicemos challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461865","doi":"https://doi.org/10.1109/slt61566.2024.10832315"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832315","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":null,"display_name":"Kaito Baba","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":true,"raw_author_name":"Kaito Baba","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068962900","display_name":"Wataru Nakata","orcid":"https://orcid.org/0000-0003-3953-6534"},"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"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042731264","display_name":"Yuki Saito","orcid":"https://orcid.org/0000-0002-4825-7783"},"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":"Yuki Saito","raw_affiliation_strings":["The University of Tokyo,Japan"],"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"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":6.9636,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.97425779,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"818","last_page":"824"},"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":0.9993000030517578,"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":0.9955999851226807,"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/naturalness","display_name":"Naturalness","score":0.9582351446151733},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6728670001029968},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6325433254241943},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6152946352958679},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6085197329521179},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5467379093170166},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.49001064896583557},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4239004850387573},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4218527674674988},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3240302503108978}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9582351446151733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6728670001029968},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6325433254241943},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6152946352958679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6085197329521179},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5467379093170166},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.49001064896583557},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4239004850387573},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4218527674674988},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3240302503108978},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"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/slt61566.2024.10832315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832315","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2060277733","https://openalex.org/W2108598243","https://openalex.org/W2592497314","https://openalex.org/W2786267588","https://openalex.org/W2808631503","https://openalex.org/W2972394484","https://openalex.org/W3096383643","https://openalex.org/W3196225973","https://openalex.org/W3202278141","https://openalex.org/W4214592090","https://openalex.org/W4225956675","https://openalex.org/W4296068974","https://openalex.org/W4297570641","https://openalex.org/W4385571424","https://openalex.org/W4385822628","https://openalex.org/W4391021560","https://openalex.org/W4391021629","https://openalex.org/W4395681711","https://openalex.org/W4395699642","https://openalex.org/W4402111789","https://openalex.org/W4406461503","https://openalex.org/W6726497184","https://openalex.org/W6745136726","https://openalex.org/W6757817989","https://openalex.org/W6780218876","https://openalex.org/W6793164127","https://openalex.org/W6862144568"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W4206357785","https://openalex.org/W4281381188","https://openalex.org/W2951211570","https://openalex.org/W3192840557","https://openalex.org/W2108985546","https://openalex.org/W2081919107"],"abstract_inverted_index":{"We":[0,69,140],"present":[1],"our":[2,50,108,146,154],"system":[3,14,51,110],"(denoted":[4],"as":[5],"T05)":[6],"for":[7,17,35,91],"the":[8,18,26,60,88,96,103,125,143],"VoiceMOS":[9],"Challenge":[10],"(VMC)":[11],"2024.":[12],"Our":[13],"was":[15],"designed":[16],"VMC":[19,104],"2024":[20,105],"Track":[21,106],"1,":[22,107],"which":[23],"focused":[24],"on":[25],"accurate":[27],"prediction":[28,94],"of":[29,62,79,98,117,145,153],"naturalness":[30],"mean":[31],"opinion":[32],"score":[33],"(MOS)":[34],"high-quality":[36],"synthetic":[37,63],"speech.":[38],"In":[39,102],"addition":[40],"to":[41,58,134,149],"a":[42,53,130],"pretrained":[43,54],"self-supervised":[44],"learning":[45],"(SSL)-based":[46],"speech":[47,64,67],"feature":[48,56],"extractor,":[49],"incorporates":[52],"image":[55],"extractor":[57],"capture":[59],"difference":[61,132],"observed":[65],"in":[66,114,124],"spectrograms.":[68],"first":[70,112],"separately":[71],"train":[72],"two":[73,89,99],"MOS":[74,93],"predictors":[75,90],"that":[76],"use":[77],"either":[78],"an":[80],"SSL-based":[81],"or":[82],"spectrogram-based":[83],"feature.":[84],"Then,":[85],"we":[86],"fine-tune":[87],"better":[92],"using":[95],"fusion":[97],"extracted":[100],"features.":[101],"T05":[109],"achieved":[111],"place":[113,123],"7":[115],"out":[116],"16":[118],"evaluation":[119],"metrics":[120],"and":[121,138],"second":[122],"remaining":[126],"9":[127],"metrics,":[128],"with":[129],"significant":[131],"compared":[133],"those":[135],"ranked":[136],"third":[137],"below.":[139],"also":[141],"report":[142],"results":[144],"ablation":[147],"study":[148],"investigate":[150],"essential":[151],"factors":[152],"system.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":11}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}