{"id":"https://openalex.org/W4386763795","doi":"https://doi.org/10.1109/waspaa58266.2023.10248127","title":"Diff-Pitcher: Diffusion-Based Singing Voice Pitch Correction","display_name":"Diff-Pitcher: Diffusion-Based Singing Voice Pitch Correction","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386763795","doi":"https://doi.org/10.1109/waspaa58266.2023.10248127"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa58266.2023.10248127","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/waspaa58266.2023.10248127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5048171604","display_name":"Jiarui Hai","orcid":"https://orcid.org/0000-0001-9968-7372"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiarui Hai","raw_affiliation_strings":["Johns Hopkins University,Laboratory for Computational Auditory Perception,Baltimore,USA","Laboratory for Computational Auditory Perception, Johns Hopkins University, Baltimore, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Laboratory for Computational Auditory Perception,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Laboratory for Computational Auditory Perception, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038788686","display_name":"Mounya Elhilali","orcid":"https://orcid.org/0000-0003-2597-738X"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mounya Elhilali","raw_affiliation_strings":["Johns Hopkins University,Laboratory for Computational Auditory Perception,Baltimore,USA","Laboratory for Computational Auditory Perception, Johns Hopkins University, Baltimore, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Laboratory for Computational Auditory Perception,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Laboratory for Computational Auditory Perception, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048171604"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.3843,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56540293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.7701372504234314},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.7701318264007568},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7376884818077087},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.619706392288208},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5594124794006348},{"id":"https://openalex.org/keywords/pitch-control","display_name":"Pitch control","score":0.48376914858818054},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.4168423116207123},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.24320581555366516},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.0829630196094513}],"concepts":[{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.7701372504234314},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.7701318264007568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7376884818077087},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.619706392288208},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5594124794006348},{"id":"https://openalex.org/C2778330180","wikidata":"https://www.wikidata.org/wiki/Q2027065","display_name":"Pitch control","level":3,"score":0.48376914858818054},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.4168423116207123},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.24320581555366516},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0829630196094513},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C78600449","wikidata":"https://www.wikidata.org/wiki/Q43302","display_name":"Wind power","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa58266.2023.10248127","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/waspaa58266.2023.10248127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1563089615","https://openalex.org/W2070202086","https://openalex.org/W2148228080","https://openalex.org/W2425246712","https://openalex.org/W2471520273","https://openalex.org/W2963091184","https://openalex.org/W2963786016","https://openalex.org/W3015759143","https://openalex.org/W3036167779","https://openalex.org/W3123097577","https://openalex.org/W3139049060","https://openalex.org/W3158762648","https://openalex.org/W3202871751","https://openalex.org/W3204602440","https://openalex.org/W3207666419","https://openalex.org/W4221153221","https://openalex.org/W4281736089","https://openalex.org/W4285345683","https://openalex.org/W4292120191","https://openalex.org/W4296068763","https://openalex.org/W4311000453","https://openalex.org/W4318752004","https://openalex.org/W4372262501","https://openalex.org/W4385245566","https://openalex.org/W6633684334","https://openalex.org/W6739901393","https://openalex.org/W6779823529","https://openalex.org/W6782760101","https://openalex.org/W6792695861","https://openalex.org/W6802169104","https://openalex.org/W6802527329","https://openalex.org/W6838843145","https://openalex.org/W6842057974","https://openalex.org/W6847363464","https://openalex.org/W6849109464","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W172797710","https://openalex.org/W2500371832","https://openalex.org/W1524071955","https://openalex.org/W2040048036","https://openalex.org/W2607529793","https://openalex.org/W2978163245","https://openalex.org/W3033263360","https://openalex.org/W2072526973","https://openalex.org/W4223504734"],"abstract_inverted_index":{"Pitch":[0,29],"correction":[1,30,168],"is":[2],"the":[3,7,46,49,54,65,69,116,119,183],"process":[4,55],"of":[5,10,34,45,56,68,118,133],"adjusting":[6],"original":[8,37],"pitch":[9,38,40,51,86,107,134,138,147,156,167,179,184],"a":[11,26,85,105],"recording":[12],"or":[13,24],"live":[14],"performance":[15],"in":[16,131,150,162,187],"order":[17],"to":[18,21,60,96,104,189],"fit":[19],"it":[20,73],"specific":[22],"key":[23],"match":[25],"target":[27,50,106],"profile.":[28],"systems":[31,169],"typical":[32],"consist":[33],"several":[35],"stages:":[36],"estimation,":[39],"curve":[41],"modification,":[42],"and":[43,75,93,99,111,128,136,152,164,170],"resynthesis":[44,57],"audio":[47],"with":[48,154],"curve.":[52],"Unfortunately,":[53],"often":[58],"leads":[59],"significant":[61],"artifacts":[62],"that":[63,89,143],"degrade":[64],"overall":[66],"quality":[67],"modified":[70],"audio,":[71],"rendering":[72],"unnatural":[74],"unpleasant.":[76],"In":[77],"this":[78],"work,":[79],"we":[80,122,159,181],"introduce":[81],"Diff-Pitcher<sup":[82],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[83],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>,":[84],"control":[87,148],"model":[88],"leverages":[90],"diffusion":[91],"modeling":[92],"source-filter":[94],"mechanisms":[95],"generate":[97],"high-quality":[98],"natural-sounding":[100],"voice":[101],"signal":[102],"matched":[103],"while":[108],"ensuring":[109],"content":[110],"timbre":[112],"consistency.":[113],"To":[114],"demonstrate":[115],"effectiveness":[117],"proposed":[120,186],"method,":[121],"evaluate":[123],"Diff-Pitcher":[124,144,161],"by":[125],"both":[126],"subjective":[127],"objective":[129],"experiments":[130],"scenarios":[132],"shifting":[135],"automatic":[137,166,178],"correction.":[139],"Our":[140],"results":[141],"show":[142],"outperforms":[145],"previous":[146],"methods":[149],"sound-quality":[151],"naturalness":[153],"great":[155],"controllability.":[157],"Furthermore,":[158],"apply":[160],"template-based":[163],"score-based":[165,177],"explore":[171],"their":[172],"application":[173],"potentials.":[174],"Meanwhile,":[175],"for":[176],"correction,":[180],"improve":[182],"predictor":[185],"KaraTuner":[188],"handle":[190],"variable-length":[191],"inputs.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}