{"id":"https://openalex.org/W2937993361","doi":"https://doi.org/10.21437/interspeech.2019-2003","title":"MOSNet: Deep Learning-Based Objective Assessment for Voice Conversion","display_name":"MOSNet: Deep Learning-Based Objective Assessment for Voice Conversion","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2937993361","doi":"https://doi.org/10.21437/interspeech.2019-2003","mag":"2937993361"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2003","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://lirias.kuleuven.be/handle/20.500.12942/711453","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039839551","display_name":"Chen-Chou Lo","orcid":"https://orcid.org/0009-0001-0072-7213"},"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":true,"raw_author_name":"Chen-Chou Lo","raw_affiliation_strings":["Academia Sinica"],"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071471469","display_name":"Szu\u2010Wei Fu","orcid":"https://orcid.org/0000-0002-3487-8212"},"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":"Szu-Wei Fu","raw_affiliation_strings":["Academia Sinica"],"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]},{"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/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":"Wen-Chin Huang","raw_affiliation_strings":["Academia Sinica"],"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327839","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8246-0606"},"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":"Xin Wang","raw_affiliation_strings":["Academia Sinica"],"affiliations":[{"raw_affiliation_string":"Academia Sinica","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/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":"Junichi Yamagishi","raw_affiliation_strings":["Academia Sinica"],"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"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":"Yu Tsao","raw_affiliation_strings":["National Institute of Informatics,"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"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":"Hsin-Min Wang","raw_affiliation_strings":["National Institute of Informatics,"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5039839551"],"corresponding_institution_ids":["https://openalex.org/I84653119"],"apc_list":null,"apc_paid":null,"fwci":1.5913,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.87546721,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1541","last_page":"1545"},"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":0.9984999895095825,"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":0.9944000244140625,"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/mean-opinion-score","display_name":"Mean opinion score","score":0.789847731590271},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7623032927513123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6680511236190796},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6543207168579102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.56385737657547},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5401910543441772},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5250413417816162},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5110741853713989},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4981880187988281},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.46508875489234924},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.46068647503852844},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4551028311252594},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.44799041748046875},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4064238667488098},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.18531930446624756},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16417962312698364},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1301906704902649},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08393499255180359}],"concepts":[{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.789847731590271},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7623032927513123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6680511236190796},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6543207168579102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.56385737657547},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5401910543441772},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5250413417816162},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5110741853713989},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4981880187988281},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.46508875489234924},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.46068647503852844},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4551028311252594},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.44799041748046875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4064238667488098},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.18531930446624756},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16417962312698364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1301906704902649},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08393499255180359},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2019-2003","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:20.500.12942/711453","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/20.500.12942/711453","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Interspeech Conference, AUSTRIA, Graz, 15-19 September 2019","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:1904.08352","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.08352","pdf_url":"https://arxiv.org/pdf/1904.08352","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2937993361","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1904.08352","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1904.08352","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.08352","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:lirias2repo.kuleuven.be:20.500.12942/711453","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/20.500.12942/711453","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Interspeech Conference, AUSTRIA, Graz, 15-19 September 2019","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Quality Education","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/W1552314771","https://openalex.org/W1600744878","https://openalex.org/W1665214252","https://openalex.org/W1995945562","https://openalex.org/W2075843680","https://openalex.org/W2078483536","https://openalex.org/W2086381917","https://openalex.org/W2095705004","https://openalex.org/W2107223151","https://openalex.org/W2107860279","https://openalex.org/W2140651276","https://openalex.org/W2398826216","https://openalex.org/W2511311723","https://openalex.org/W2557915412","https://openalex.org/W2577886607","https://openalex.org/W2808694371","https://openalex.org/W2889351461","https://openalex.org/W2889442120","https://openalex.org/W2922332774","https://openalex.org/W2963035245","https://openalex.org/W2963403924","https://openalex.org/W2964121744"],"related_works":["https://openalex.org/W2972394484","https://openalex.org/W3155424487","https://openalex.org/W2257732371","https://openalex.org/W1934927571","https://openalex.org/W2080708395","https://openalex.org/W2286857798","https://openalex.org/W2069320166","https://openalex.org/W2943190612","https://openalex.org/W2357188058","https://openalex.org/W408749025","https://openalex.org/W259826384","https://openalex.org/W2060592919","https://openalex.org/W2294459443","https://openalex.org/W2121698373","https://openalex.org/W2004132380","https://openalex.org/W3016039577","https://openalex.org/W2110045522","https://openalex.org/W824467349","https://openalex.org/W2000130062","https://openalex.org/W1880248041"],"abstract_inverted_index":{"Existing":[0],"objective":[1],"evaluation":[2],"metrics":[3],"for":[4,170],"voice":[5],"conversion":[6],"(VC)":[7],"are":[8,71,96,138],"not":[9,23],"always":[10],"correlated":[11,98,110,141],"with":[12,19,99,111,142],"human":[13,43,100,112,143,172],"perception.":[14],"Therefore,":[15],"training":[16],"VC":[17,164],"models":[18,40,56,70,151],"such":[20],"criteria":[21],"may":[22],"effectively":[24],"improve":[25],"naturalness":[26],"and":[27,52,129],"similarity":[28,127],"of":[29,45,78,92,163],"converted":[30,46],"speech.":[31,47],"In":[32],"this":[33],"paper,":[34],"we":[35,120],"propose":[36],"deep":[37],"learning-based":[38],"assessment":[39],"to":[41,57,124,159,166],"predict":[42,125],"ratings":[44,102,114],"We":[48],"adopt":[49],"the":[50,79,89,93,104,116,126,130,135,149,161,168],"convolutional":[51],"recurrent":[53],"neural":[54],"network":[55],"build":[58],"a":[59,156],"mean":[60],"opinion":[61],"score":[62],"(MOS)":[63],"predictor,":[64],"termed":[65],"as":[66,155],"MOSNet.":[67],"The":[68],"proposed":[69,94,150],"tested":[72],"on":[73],"large-scale":[74],"listening":[75],"test":[76],"results":[77,86,132,146],"Voice":[80],"Conversion":[81],"Challenge":[82],"(VCC)":[83],"2018.":[84],"Experimental":[85],"show":[87,133],"that":[88,134,148],"predicted":[90,136],"scores":[91,137],"MOSNet":[95,123],"highly":[97],"MOS":[101,113,162],"at":[103,115],"system":[105],"level":[106],"while":[107],"being":[108],"fairly":[109,140],"utterance":[117],"level.":[118],"Meanwhile,":[119],"have":[121],"modified":[122],"scores,":[128],"preliminary":[131],"also":[139],"ratings.":[144],"These":[145],"confirm":[147],"could":[152],"be":[153],"used":[154],"computational":[157],"evaluator":[158],"measure":[160],"systems":[165],"reduce":[167],"need":[169],"expensive":[171],"rating.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}