{"id":"https://openalex.org/W3207932315","doi":"https://doi.org/10.1109/icassp43922.2022.9747222","title":"LDNet: Unified Listener Dependent Modeling in MOS Prediction for Synthetic Speech","display_name":"LDNet: Unified Listener Dependent Modeling in MOS Prediction for Synthetic Speech","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3207932315","doi":"https://doi.org/10.1109/icassp43922.2022.9747222","mag":"3207932315"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747222","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/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/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/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"]}]},{"author_position":"last","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"]}]}],"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":51,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"896","last_page":"900"},"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":0.9998999834060669,"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/T10863","display_name":"Voice and Speech Disorders","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"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/mean-opinion-score","display_name":"Mean opinion score","score":0.840095043182373},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7564917802810669},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6951917409896851},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6674612164497375},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5305058360099792},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5125081539154053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5119820237159729},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4632284641265869},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44576749205589294},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4130437970161438},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32737404108047485},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08407530188560486},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07380145788192749}],"concepts":[{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.840095043182373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7564917802810669},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6951917409896851},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6674612164497375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5305058360099792},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5125081539154053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5119820237159729},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4632284641265869},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44576749205589294},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4130437970161438},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32737404108047485},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08407530188560486},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07380145788192749},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747222","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":[{"display_name":"Quality Education","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2473388484","https://openalex.org/W2962780374","https://openalex.org/W2963035245","https://openalex.org/W2963163009","https://openalex.org/W2972394484","https://openalex.org/W2982083293","https://openalex.org/W3016160783","https://openalex.org/W3082130377","https://openalex.org/W3097206152","https://openalex.org/W3129991388","https://openalex.org/W3153221018","https://openalex.org/W3161558238","https://openalex.org/W3196225973","https://openalex.org/W3198102247","https://openalex.org/W3198270377","https://openalex.org/W3202278141","https://openalex.org/W4235201968","https://openalex.org/W4395962115","https://openalex.org/W6790286634","https://openalex.org/W6794949959","https://openalex.org/W6840412704","https://openalex.org/W6865630430"],"related_works":["https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W2997121352","https://openalex.org/W4237969969","https://openalex.org/W1594297642","https://openalex.org/W2366328218","https://openalex.org/W2509366663"],"abstract_inverted_index":{"An":[0],"effective":[1],"approach":[2],"to":[3,13,142],"automatically":[4],"predict":[5],"the":[6,28,40,44,64,69,73,87,108,127,133,144],"subjective":[7],"rating":[8],"for":[9,56],"synthetic":[10],"speech":[11,25,71],"is":[12,30,138,149],"train":[14],"on":[15,107],"a":[16,53,116,139],"listening":[17],"test":[18],"dataset":[19,29],"with":[20],"human-annotated":[21],"scores.":[22],"Although":[23],"each":[24],"sample":[26],"in":[27,80],"rated":[31],"by":[32],"several":[33],"listeners,":[34],"most":[35],"previous":[36],"works":[37],"only":[38],"used":[39],"mean":[41,57,134,145],"score":[42,59],"as":[43],"training":[45],"target.":[46],"In":[47],"this":[48],"work,":[49],"we":[50],"present":[51],"LDNet,":[52],"unified":[54],"framework":[55],"opinion":[58],"(MOS)":[60],"prediction":[61],"that":[62,95,132],"predicts":[63],"listener-wise":[65],"perceived":[66],"quality":[67],"given":[68],"input":[70],"and":[72,90,100,115],"listener":[74,135],"identity.":[75],"We":[76,103],"reflect":[77],"recent":[78],"advances":[79],"LD":[81],"modeling,":[82],"including":[83],"design":[84],"choices":[85],"of":[86,126],"model":[88],"architecture,":[89],"propose":[91],"two":[92],"inference":[93,136],"methods":[94],"provide":[96],"more":[97,150,154],"stable":[98],"results":[99],"efficient":[101],"computation.":[102],"conduct":[104],"systematic":[105],"experiments":[106],"voice":[109],"conversion":[110],"challenge":[111],"(VCC)":[112],"2018":[113],"benchmark":[114],"newly":[117],"collected":[118],"largescale":[119],"MOS":[120],"dataset,":[121],"providing":[122],"an":[123],"in-depth":[124],"analysis":[125],"proposed":[128],"framework.":[129],"Results":[130],"show":[131],"method":[137],"better":[140],"way":[141],"utilize":[143],"scores,":[146],"whose":[147],"effectiveness":[148],"obvious":[151],"when":[152],"having":[153],"ratings":[155],"per":[156],"sample.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}