{"id":"https://openalex.org/W4285169718","doi":"https://doi.org/10.1109/access.2022.3175810","title":"Learning to Maximize Speech Quality Directly Using MOS Prediction for Neural Text-to-Speech","display_name":"Learning to Maximize Speech Quality Directly Using MOS Prediction for Neural Text-to-Speech","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285169718","doi":"https://doi.org/10.1109/access.2022.3175810"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3175810","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3175810","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09775804.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09775804.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059450470","display_name":"Yeunju Choi","orcid":"https://orcid.org/0000-0003-2192-2680"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeunju Choi","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-2192-2680","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101457226","display_name":"Youngmoon Jung","orcid":"https://orcid.org/0000-0002-4321-379X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngmoon Jung","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-4321-379X","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033502618","display_name":"Young-Joo Suh","orcid":"https://orcid.org/0000-0001-7208-1709"},"institutions":[{"id":"https://openalex.org/I24062138","display_name":"Konkuk University","ror":"https://ror.org/025h1m602","country_code":"KR","type":"education","lineage":["https://openalex.org/I24062138"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngjoo Suh","raw_affiliation_strings":["Voice Group, Konan Technology Inc., Seoul, South Korea","Voice Group, Konan Technology Inc., Seoul 06627, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Voice Group, Konan Technology Inc., Seoul, South Korea","institution_ids":["https://openalex.org/I24062138"]},{"raw_affiliation_string":"Voice Group, Konan Technology Inc., Seoul 06627, South Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066573438","display_name":"Hoirin Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hoirin Kim","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-8787-6982","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.2754,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.8227369,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"10","issue":null,"first_page":"52621","last_page":"52629"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9994000196456909,"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":0.9980000257492065,"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":0.8263098001480103},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8189583420753479},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7817337512969971},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6960394382476807},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.6913127899169922},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6773500442504883},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5287955403327942},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5244379639625549},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4719592332839966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42932048439979553},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.42140626907348633},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4116586446762085}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8263098001480103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8189583420753479},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7817337512969971},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6960394382476807},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.6913127899169922},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6773500442504883},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5287955403327942},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5244379639625549},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4719592332839966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42932048439979553},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.42140626907348633},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4116586446762085},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2022.3175810","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3175810","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09775804.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2011.01174","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.01174","pdf_url":"https://arxiv.org/pdf/2011.01174","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":"pmh:oai:doaj.org/article:94c605add4db4b9fa8fb5f63361d4929","is_oa":true,"landing_page_url":"https://doaj.org/article/94c605add4db4b9fa8fb5f63361d4929","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 52621-52629 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3175810","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3175810","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09775804.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G3523231294","display_name":null,"funder_award_id":"2021R1A2C1014044","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G6450633841","display_name":null,"funder_award_id":"2021R1A2C1014044","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285169718.pdf","grobid_xml":"https://content.openalex.org/works/W4285169718.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2067295501","https://openalex.org/W2075843680","https://openalex.org/W2078483536","https://openalex.org/W2093107730","https://openalex.org/W2112659417","https://openalex.org/W2331128040","https://openalex.org/W2473388484","https://openalex.org/W2519091744","https://openalex.org/W2767052532","https://openalex.org/W2769810959","https://openalex.org/W2891607145","https://openalex.org/W2892110446","https://openalex.org/W2892129657","https://openalex.org/W2903739847","https://openalex.org/W2942807473","https://openalex.org/W2946200149","https://openalex.org/W2963035245","https://openalex.org/W2963289467","https://openalex.org/W2963542120","https://openalex.org/W2963656735","https://openalex.org/W2963920537","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2971417062","https://openalex.org/W2972394484","https://openalex.org/W2985518820","https://openalex.org/W2987989623","https://openalex.org/W3015338123","https://openalex.org/W3016160783","https://openalex.org/W3033935508","https://openalex.org/W3047992192","https://openalex.org/W3095545636","https://openalex.org/W3096159803","https://openalex.org/W3098606562","https://openalex.org/W3103902067","https://openalex.org/W3114770456","https://openalex.org/W3147454823","https://openalex.org/W3160289600","https://openalex.org/W3162046328","https://openalex.org/W3168542456","https://openalex.org/W4235201968","https://openalex.org/W4239251463","https://openalex.org/W4294619240","https://openalex.org/W6640174519","https://openalex.org/W6735013348","https://openalex.org/W6763832098","https://openalex.org/W6767111847","https://openalex.org/W6769995984","https://openalex.org/W6779071432"],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W4252942110","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W4391272374","https://openalex.org/W4403759994","https://openalex.org/W4400309480","https://openalex.org/W2549308614","https://openalex.org/W2081919107"],"abstract_inverted_index":{"Although":[0],"recent":[1],"neural":[2],"text-to-speech":[3],"(TTS)":[4],"systems":[5],"have":[6],"achieved":[7],"high-quality":[8],"speech":[9,41,62,91,115],"synthesis,":[10],"there":[11],"are":[12],"cases":[13],"where":[14],"a":[15,36,45,72,82],"TTS":[16,46,83,108],"system":[17],"generates":[18],"low-quality":[19],"speech,":[20],"mainly":[21],"caused":[22],"by":[23,43],"limited":[24],"training":[25,44],"data":[26],"or":[27,111,125],"information":[28],"loss":[29],"during":[30],"knowledge":[31],"distillation.":[32],"Therefore,":[33],"we":[34],"propose":[35],"novel":[37],"method":[38,100],"to":[39,85],"improve":[40],"quality":[42,63,116],"model":[47,78,84,109,126],"under":[48],"the":[49,56,59,66,87,93,107,112,122,132],"supervision":[50],"of":[51,89,106,114,148],"perceptual":[52],"loss,":[53],"which":[54],"measures":[55],"distance":[57],"between":[58],"maximum":[60],"possible":[61],"score":[64,75],"and":[65,79,118,134,151],"predicted":[67],"one.":[68],"We":[69],"first":[70],"pre-train":[71],"mean":[73],"opinion":[74],"(MOS)":[76],"prediction":[77,96],"then":[80],"train":[81],"maximize":[86],"MOS":[88,95,133],"synthesized":[90],"using":[92],"pre-trained":[94],"model.":[97],"The":[98,128],"proposed":[99,141],"can":[101],"be":[102],"applied":[103],"independently":[104],"regardless":[105],"architecture":[110],"cause":[113],"degradation":[117],"efficiently":[119],"without":[120],"increasing":[121],"inference":[123],"time":[124],"complexity.":[127],"evaluation":[129],"results":[130],"for":[131],"phone":[135],"error":[136],"rate":[137],"demonstrate":[138],"that":[139],"our":[140],"approach":[142],"improves":[143],"previous":[144],"models":[145],"in":[146],"terms":[147],"both":[149],"naturalness":[150],"intelligibility.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}