{"id":"https://openalex.org/W3207666419","doi":"https://doi.org/10.21437/interspeech.2022-939","title":"KaraTuner: Towards End-to-End Natural Pitch Correction for Singing Voice in Karaoke","display_name":"KaraTuner: Towards End-to-End Natural Pitch Correction for Singing Voice in Karaoke","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W3207666419","doi":"https://doi.org/10.21437/interspeech.2022-939","mag":"3207666419"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-939","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-939","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5001776951","display_name":"Xiaobin Zhuang","orcid":"https://orcid.org/0000-0002-0285-6705"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobin Zhuang","raw_affiliation_strings":["Tencent Music Entertainment Lyra Lab, Shenzhen, China","{aaronzhuang,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Music Entertainment Lyra Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"{aaronzhuang,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021023563","display_name":"Huiran Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huiran Yu","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012377192","display_name":"Weifeng Zhao","orcid":"https://orcid.org/0000-0003-2689-0251"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifeng Zhao","raw_affiliation_strings":["Tencent Music Entertainment Lyra Lab, Shenzhen, China","{aaronzhuang,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Music Entertainment Lyra Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"{aaronzhuang,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063092424","display_name":"Tao Jiang","orcid":"https://orcid.org/0000-0001-8031-1287"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Jiang","raw_affiliation_strings":["Tencent Music Entertainment Lyra Lab, Shenzhen, China","{aaronzhuang,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Music Entertainment Lyra Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"{aaronzhuang,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110055668","display_name":"Peng Hu","orcid":"https://orcid.org/0000-0003-0186-2190"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Hu","raw_affiliation_strings":["Tencent Music Entertainment Lyra Lab, Shenzhen, China","{aaronzhuang,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Music Entertainment Lyra Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"{aaronzhuang,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5526,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.57926578,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4262","last_page":"4266"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9993000030517578,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8096281290054321},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6113121509552002},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6105246543884277},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.5789680480957031},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5068762898445129},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2674961984157562},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1233365535736084},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.0487196147441864},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.044971853494644165}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8096281290054321},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6113121509552002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6105246543884277},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5789680480957031},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5068762898445129},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2674961984157562},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1233365535736084},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0487196147441864},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.044971853494644165},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-939","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-939","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W126257978","https://openalex.org/W1557133539","https://openalex.org/W1558306184","https://openalex.org/W2093824445","https://openalex.org/W2093840616","https://openalex.org/W2102488493","https://openalex.org/W2118774185","https://openalex.org/W2150696241","https://openalex.org/W2425246712","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2586947700","https://openalex.org/W2778460379","https://openalex.org/W2785075253","https://openalex.org/W2891198685","https://openalex.org/W2949382160","https://openalex.org/W2963091184","https://openalex.org/W2963175743","https://openalex.org/W2963300588","https://openalex.org/W2963403868","https://openalex.org/W2963786016","https://openalex.org/W2964307104","https://openalex.org/W3000389243","https://openalex.org/W3015338123","https://openalex.org/W3015759143","https://openalex.org/W3035430139","https://openalex.org/W3092028330","https://openalex.org/W3097514409","https://openalex.org/W3137000704","https://openalex.org/W3171962689","https://openalex.org/W3202871751","https://openalex.org/W3206191467","https://openalex.org/W4221153221","https://openalex.org/W4287125610","https://openalex.org/W4298580827","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2359916600","https://openalex.org/W2380929698"],"abstract_inverted_index":{"An":[0],"automatic":[1],"pitch":[2,11,15,50,61,80,82,95,130],"correction":[3,131],"system":[4],"typically":[5],"includes":[6],"several":[7],"stages,":[8],"such":[9],"as":[10],"extraction,":[12],"deviation":[13],"estimation,":[14],"shift":[16],"processing,":[17],"and":[18,30,52,62,86,105,119,136,150,161],"cross-fade":[19],"smoothing.However,":[20],"designing":[21],"these":[22],"components":[23],"with":[24,154],"strategies":[25],"often":[26],"requires":[27],"domain":[28],"expertise":[29],"they":[31],"are":[32],"likely":[33],"to":[34,78,97],"fail":[35],"on":[36,114],"corner":[37],"cases.In":[38],"this":[39],"paper,":[40],"we":[41],"present":[42],"KaraTuner,":[43],"an":[44],"end-to-end":[45],"neural":[46],"architecture":[47],"that":[48,140],"predicts":[49],"curve":[51],"resynthesizes":[53],"the":[54,59,67,94,102,120,128,141,155],"singing":[55],"voice":[56],"directly":[57],"from":[58,66],"tuned":[60],"vocal":[63,103],"spectrum":[64,104],"extracted":[65],"original":[68],"recordings.Several":[69],"vital":[70],"technical":[71],"points":[72],"have":[73],"been":[74],"introduced":[75],"in":[76,93,101,147],"KaraTuner":[77],"ensure":[79],"accuracy,":[81],"naturalness,":[83],"timbre":[84,148],"consistency,":[85],"sound":[87,151],"quality.A":[88],"feed-forward":[89],"Transformer":[90],"is":[91],"employed":[92],"predictor":[96],"capture":[98],"longterm":[99],"dependencies":[100],"musical":[106],"note.We":[107],"also":[108],"develop":[109],"a":[110,115,124],"pitch-controllable":[111],"vocoder":[112,143,160],"based":[113],"novel":[116],"source-filter":[117],"block":[118],"Fre-GAN":[121],"architecture.KaraTuner":[122],"obtains":[123],"higher":[125],"preference":[126],"than":[127],"rule-based":[129],"approach":[132],"through":[133],"A/B":[134],"tests,":[135],"perceptual":[137],"experiments":[138],"show":[139],"proposed":[142],"achieves":[144],"significant":[145],"advantages":[146],"consistency":[149],"quality":[152],"compared":[153],"parametric":[156],"WORLD":[157],"vocoder,":[158],"phase":[159],"CLPC":[162],"vocoder.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}