{"id":"https://openalex.org/W3196760057","doi":"https://doi.org/10.21437/interspeech.2021-239","title":"N-Singer: A Non-Autoregressive Korean Singing Voice Synthesis System for Pronunciation Enhancement","display_name":"N-Singer: A Non-Autoregressive Korean Singing Voice Synthesis System for Pronunciation Enhancement","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196760057","doi":"https://doi.org/10.21437/interspeech.2021-239","mag":"3196760057"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-239","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5065639840","display_name":"Gyeong-Hoon Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Gyeong-Hoon Lee","raw_affiliation_strings":["Speech AI Lab., AI Center, NCSOFT, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Speech AI Lab., AI Center, NCSOFT, Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400958","display_name":"Taewoo Kim","orcid":"https://orcid.org/0000-0003-4290-6460"},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tae-Woo Kim","raw_affiliation_strings":["Speech AI Lab., AI Center, NCSOFT, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Speech AI Lab., AI Center, NCSOFT, Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046330926","display_name":"Hanbin Bae","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hanbin Bae","raw_affiliation_strings":["Speech AI Lab., AI Center, NCSOFT, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Speech AI Lab., AI Center, NCSOFT, Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747577","display_name":"Minji Lee","orcid":"https://orcid.org/0000-0003-4261-875X"},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Min-Ji Lee","raw_affiliation_strings":["Speech AI Lab., AI Center, NCSOFT, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Speech AI Lab., AI Center, NCSOFT, Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028488704","display_name":"Young-Ik Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Young-Ik Kim","raw_affiliation_strings":["Speech AI Lab., AI Center, NCSOFT, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Speech AI Lab., AI Center, NCSOFT, Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052468556","display_name":"Hoon Young Cho","orcid":"https://orcid.org/0000-0002-6850-6580"},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hoon-Young Cho","raw_affiliation_strings":["Speech AI Lab., AI Center, NCSOFT, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Speech AI Lab., AI Center, NCSOFT, Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5065639840"],"corresponding_institution_ids":["https://openalex.org/I4210135449"],"apc_list":null,"apc_paid":null,"fwci":2.3116,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90335216,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1589","last_page":"1593"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9980999827384949,"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":0.9979000091552734,"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/singing","display_name":"Singing","score":0.7792112827301025},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7779527306556702},{"id":"https://openalex.org/keywords/voice","display_name":"Voice","score":0.7328125834465027},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7200846076011658},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7160627245903015},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6041727066040039},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.562320351600647},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5167385935783386},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.49395376443862915},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.48322638869285583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35775330662727356},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.25550544261932373},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1139785647392273},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10444021224975586},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10087698698043823},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07183137536048889}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7792112827301025},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7779527306556702},{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.7328125834465027},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7200846076011658},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7160627245903015},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6041727066040039},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.562320351600647},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5167385935783386},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.49395376443862915},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.48322638869285583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35775330662727356},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.25550544261932373},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1139785647392273},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10444021224975586},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10087698698043823},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07183137536048889},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-239","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2095705004","https://openalex.org/W2471520273","https://openalex.org/W2515336442","https://openalex.org/W2594814449","https://openalex.org/W2767052532","https://openalex.org/W2778460379","https://openalex.org/W2787579267","https://openalex.org/W2889244839","https://openalex.org/W2946200149","https://openalex.org/W2963285578","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2973046048","https://openalex.org/W2981413347","https://openalex.org/W3015338123","https://openalex.org/W3015499232","https://openalex.org/W3015516707","https://openalex.org/W3097514409","https://openalex.org/W3097777922","https://openalex.org/W3133525064","https://openalex.org/W3160326269","https://openalex.org/W4252684946","https://openalex.org/W4287672314","https://openalex.org/W4288265053","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W4394643672"],"related_works":["https://openalex.org/W2036753972","https://openalex.org/W1996861825","https://openalex.org/W2079621619","https://openalex.org/W2046280377","https://openalex.org/W4388535697","https://openalex.org/W2497205885","https://openalex.org/W2036128733","https://openalex.org/W1976086899","https://openalex.org/W2374220079","https://openalex.org/W2377483540"],"abstract_inverted_index":{"Recently,":[0],"end-to-end":[1],"Korean":[2,35,44],"singing":[3,12,36,45,127],"voice":[4,37,128],"systems":[5,15],"have":[6],"been":[7],"designed":[8],"to":[9,39,81,104],"generate":[10],"realistic":[11],"voices.However,":[13],"these":[14],"still":[16],"suffer":[17],"from":[18],"a":[19,33,51,54,87,125,132],"lack":[20],"of":[21,25,50,89,109,115],"robustness":[22],"in":[23,47,63,96,129],"terms":[24],"pronunciation":[26,135],"accuracy.In":[27],"this":[28],"paper,":[29],"we":[30],"propose":[31],"N-Singer,":[32],"nonautoregressive":[34],"system,":[38],"synthesize":[40,124],"accurate":[41,68,134],"and":[42,58,74,92,112],"pronounced":[43],"voices":[46],"parallel.N-Singer":[48],"consists":[49],"Transformer-based":[52,90],"mel-generator,":[53],"convolutional":[55,93],"network-based":[56],"postnet,":[57],"voicing-aware":[59,99],"discriminators.It":[60],"can":[61,123],"contribute":[62],"the":[64,106,137],"following":[65],"ways.First,":[66],"for":[67],"pronunciation,":[69],"N-Singer":[70,85,122],"separately":[71],"models":[72],"linguistic":[73],"pitch":[75],"information":[76],"without":[77],"other":[78],"acoustic":[79],"features.Second,":[80],"achieve":[82],"improved":[83],"mel-spectrograms,":[84],"uses":[86],"combination":[88],"modules":[91],"networkbased":[94],"modules.Third,":[95],"adversarial":[97],"training,":[98],"conditional":[100],"discriminators":[101],"are":[102],"used":[103],"capture":[105],"harmonic":[107],"features":[108],"voiced":[110],"segments":[111],"noise":[113],"components":[114],"unvoiced":[116],"segments.The":[117],"experimental":[118],"results":[119],"prove":[120],"that":[121],"natural":[126],"parallel":[130],"with":[131],"more":[133],"than":[136],"baseline":[138],"model.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
