{"id":"https://openalex.org/W3015759143","doi":"https://doi.org/10.1109/icassp40776.2020.9054308","title":"Deep Autotuner: A Pitch Correcting Network for Singing Performances","display_name":"Deep Autotuner: A Pitch Correcting Network for Singing Performances","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015759143","doi":"https://doi.org/10.1109/icassp40776.2020.9054308","mag":"3015759143"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5072310429","display_name":"Sanna Wager","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanna Wager","raw_affiliation_strings":["Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010445045","display_name":"George Tzanetakis","orcid":"https://orcid.org/0000-0002-6844-7912"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"George Tzanetakis","raw_affiliation_strings":["Department of Computer Science, University of Victoria, Victoria, BC, Canada","University of Victoria, Dept. of Computer Science, Victoria, BC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Victoria, Victoria, BC, Canada","institution_ids":["https://openalex.org/I212119943"]},{"raw_affiliation_string":"University of Victoria, Dept. of Computer Science, Victoria, BC, Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043273491","display_name":"Cheng-i Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng-i Wang","raw_affiliation_strings":["Smule, Inc, San Francisco, CA, USA","Smule, Inc,San Francisco,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Smule, Inc, San Francisco, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Smule, Inc,San Francisco,CA,USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064582903","display_name":"Minje Kim","orcid":"https://orcid.org/0000-0003-3513-8328"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minje Kim","raw_affiliation_strings":["Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8075,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.86733002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"246","last_page":"250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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/T11309","display_name":"Music and Audio Processing","score":1.0,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8352559804916382},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.8051449060440063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7070634365081787},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6636370420455933},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5710121989250183},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5152350068092346},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4737568497657776},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4702303111553192},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.455055296421051},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.444536030292511},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4250189960002899},{"id":"https://openalex.org/keywords/improvisation","display_name":"Improvisation","score":0.4172844886779785},{"id":"https://openalex.org/keywords/relative-pitch","display_name":"Relative pitch","score":0.41690653562545776},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1961841583251953},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0764438807964325}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8352559804916382},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.8051449060440063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7070634365081787},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6636370420455933},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5710121989250183},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5152350068092346},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4737568497657776},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4702303111553192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.455055296421051},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.444536030292511},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4250189960002899},{"id":"https://openalex.org/C125468537","wikidata":"https://www.wikidata.org/wiki/Q214961","display_name":"Improvisation","level":2,"score":0.4172844886779785},{"id":"https://openalex.org/C94544720","wikidata":"https://www.wikidata.org/wiki/Q2736124","display_name":"Relative pitch","level":3,"score":0.41690653562545776},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1961841583251953},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0764438807964325},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.41999998688697815,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W1815076433","https://openalex.org/W1924770834","https://openalex.org/W1987076655","https://openalex.org/W1994459787","https://openalex.org/W2053347927","https://openalex.org/W2118774185","https://openalex.org/W2133003941","https://openalex.org/W2148228080","https://openalex.org/W2151250504","https://openalex.org/W2157331557","https://openalex.org/W2191779130","https://openalex.org/W2275207977","https://openalex.org/W2605762339","https://openalex.org/W2773294482","https://openalex.org/W2793550381","https://openalex.org/W2847144333","https://openalex.org/W2891198685","https://openalex.org/W2902737956","https://openalex.org/W2920728711","https://openalex.org/W2939190664","https://openalex.org/W2962850167","https://openalex.org/W2963786016","https://openalex.org/W2964121744","https://openalex.org/W4241145092","https://openalex.org/W4285719527","https://openalex.org/W6631190155","https://openalex.org/W6638545294","https://openalex.org/W6640212811","https://openalex.org/W6685997681","https://openalex.org/W6746836464","https://openalex.org/W6760299066","https://openalex.org/W7046240531"],"related_works":["https://openalex.org/W2052817658","https://openalex.org/W2530685530","https://openalex.org/W2146959957","https://openalex.org/W2129561254","https://openalex.org/W3208261218","https://openalex.org/W4375868962","https://openalex.org/W187317481","https://openalex.org/W1964683721","https://openalex.org/W2182631153","https://openalex.org/W2429977719"],"abstract_inverted_index":{"We":[0,98],"introduce":[1],"a":[2,51,72,79,105,128],"data-driven":[3],"approach":[4,15,33],"to":[5,45,56,137],"automatic":[6],"pitch":[7,18,59,70,132,161],"correction":[8,162],"of":[9,27,81,107,150],"solo":[10],"singing":[11,29,96,160],"performances.":[12],"The":[13,66,139],"proposed":[14,67,140],"predicts":[16],"note-wise":[17],"shifts":[19],"from":[20,35],"the":[21,24,28,57,61,95,157],"relationship":[22],"between":[23],"respective":[25],"spectrograms":[26],"and":[30,92,130],"accompaniment.":[31],"This":[32],"differs":[34],"commercial":[36],"systems,":[37],"where":[38],"vocal":[39],"track":[40],"notes":[41,83],"are":[42],"usually":[43],"shifted":[44],"be":[46],"centered":[47],"around":[48],"pitches":[49],"in":[50,85,94],"user-defined":[52],"score,":[53],"or":[54],"mapped":[55],"closest":[58],"among":[60],"twelve":[62],"equal-tempered":[63],"scale":[64],"degrees.":[65],"system":[68],"treats":[69],"as":[71],"continuous":[73],"value":[74],"rather":[75],"than":[76],"relying":[77],"on":[78,120,148,156],"set":[80],"discretized":[82],"found":[84],"musical":[86],"scores,":[87],"thus":[88],"allowing":[89],"for":[90,113,124],"improvisation":[91],"harmonization":[93],"performance.":[97],"train":[99],"our":[100],"neural":[101,142],"network":[102,143],"model":[103,117],"using":[104],"dataset":[106],"4,702":[108],"amateur":[109],"karaoke":[110],"performances":[111],"selected":[112],"good":[114],"intonation.":[115],"Our":[116],"is":[118],"trained":[119],"both":[121],"incorrect":[122],"intonation,":[123],"which":[125,134],"it":[126,135],"learns":[127,136],"correction,":[129],"intentional":[131],"variation,":[133],"preserve.":[138],"deep":[141],"with":[144],"gated":[145],"recurrent":[146],"units":[147],"top":[149],"convolutional":[151],"layers":[152],"shows":[153],"promising":[154],"performance":[155],"real-world":[158],"score-free":[159],"task-autotuning.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}