{"id":"https://openalex.org/W7224095022","doi":"https://doi.org/10.1186/s13636-026-00482-1","title":"CREPE-guided note-level melody estimation and tonal-representation analysis for monophonic humming","display_name":"CREPE-guided note-level melody estimation and tonal-representation analysis for monophonic humming","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224095022","doi":"https://doi.org/10.1186/s13636-026-00482-1"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-026-00482-1","doi":"https://doi.org/10.1186/s13636-026-00482-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-026-00482-1","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-c","jufo-1","norway-1","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s13636-026-00482-1","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083923949","display_name":"Jieran Liu","orcid":"https://orcid.org/0009-0001-6008-8687","observed_orcids":["https://orcid.org/0009-0001-6008-8687"]},"institutions":[{"id":"https://openalex.org/I4210163873","display_name":"Zhengzhou University of Industrial Technology","ror":"https://ror.org/05es8as59","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163873"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jieran Liu","raw_affiliation_strings":["Department of Artificial Intelligence, Zhengzhou University of Industrial Technology, Zhengzhou, 451150, China"],"raw_orcid":"https://orcid.org/0009-0001-6008-8687","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Zhengzhou University of Industrial Technology, Zhengzhou, 451150, China","institution_ids":["https://openalex.org/I4210163873"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160035445","display_name":"Chaoxin Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210163873","display_name":"Zhengzhou University of Industrial Technology","ror":"https://ror.org/05es8as59","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163873"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoxin Wang","raw_affiliation_strings":["Department of Artificial Intelligence, Zhengzhou University of Industrial Technology, Zhengzhou, 451150, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Zhengzhou University of Industrial Technology, Zhengzhou, 451150, China","institution_ids":["https://openalex.org/I4210163873"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160016062","display_name":"Hongyu Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210163873","display_name":"Zhengzhou University of Industrial Technology","ror":"https://ror.org/05es8as59","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163873"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyu Jiang","raw_affiliation_strings":["Department of Artificial Intelligence, Zhengzhou University of Industrial Technology, Zhengzhou, 451150, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Zhengzhou University of Industrial Technology, Zhengzhou, 451150, China","institution_ids":["https://openalex.org/I4210163873"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5083923949"],"corresponding_institution_ids":["https://openalex.org/I4210163873"],"apc_list":{"value":1890,"currency":"USD","value_usd":1890},"apc_paid":{"value":1890,"currency":"USD","value_usd":1890},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85847059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":9.999999747378752e-05,"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/T10860","display_name":"Speech and Audio Processing","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/crepes","display_name":"crepes","score":0.8259999752044678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8504999876022339},{"id":"https://openalex.org/C23161992","wikidata":"https://www.wikidata.org/wiki/Q2922301","display_name":"Hum","level":3,"score":0.8267999887466431},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6909000277519226},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5468999743461609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34119999408721924},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.25360000133514404},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23190000653266907},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.20839999616146088},{"id":"https://openalex.org/C34951282","wikidata":"https://www.wikidata.org/wiki/Q864191","display_name":"Bioacoustics","level":2,"score":0.20630000531673431}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1186/s13636-026-00482-1","doi":"https://doi.org/10.1186/s13636-026-00482-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-026-00482-1","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-c","jufo-1","norway-1","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/s13636-026-00482-1","doi":"https://doi.org/10.1186/s13636-026-00482-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-026-00482-1","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-c","jufo-1","norway-1","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W30043770","https://openalex.org/W109697837","https://openalex.org/W7019932809","https://openalex.org/W2573843158","https://openalex.org/W1542377715","https://openalex.org/W7112672913","https://openalex.org/W2507954440","https://openalex.org/W7099884960","https://openalex.org/W2312520171","https://openalex.org/W2771763364"],"abstract_inverted_index":{"Humming":[0],"is":[1,72,211,243],"a":[2,59,175,183,189],"convenient":[3],"input":[4],"for":[5],"query-by-humming":[6],"and":[7,25,41,49,53,97,104,121,132,143,197,245,282],"music-education":[8],"systems,":[9],"but":[10,209],"note":[11,230],"boundaries":[12],"are":[13,56,221,247],"often":[14],"weak":[15],"because":[16,217],"amateur":[17],"performances":[18],"contain":[19],"glides,":[20],"vibrato,":[21],"short":[22],"unvoiced":[23],"gaps":[24],"intonation":[26],"error.":[27],"We":[28],"combine":[29],"the":[30,80,107,117,123,268],"full":[31],"CREPE":[32,233],"pitch":[33,139,290],"estimator":[34],"with":[35,168],"44":[36],"frame-level":[37],"pitch,":[38],"energy,":[39],"spectral-flux":[40],"voicing-context":[42],"features.":[43],"Separate":[44],"RandomForest":[45],"classifiers":[46],"estimate":[47,92],"onset":[48],"offset":[50],"probabilities.":[51],"Model":[52],"decoder":[54],"parameters":[55],"selected":[57],"within":[58,159,278],"recording-grouped":[60],"5":[61],"\\(\\times\\)":[62],"4":[63],"nested":[64,244],"cross-validation":[65],"protocol,":[66],"so":[67],"each":[68],"outer":[69],"test":[70],"recording":[71],"excluded":[73],"from":[74,171,232,288],"every":[75],"selection":[76,242],"step.":[77],"After":[78],"auditing":[79],"annotations,":[81],"38":[82,119],"MTG-QBH/Molina":[83],"recordings":[84],"contained":[85],"2152":[86],"reference":[87],"notes.":[88],"The":[89,249,263],"primary":[90],"nested-CV":[91],"achieved":[93],"micro-averaged":[94],"COnPOff,":[95],"COnP":[96],"COn":[98],"F":[99],"-measures":[100],"of":[101,162,271],"0.696,":[102],"0.842":[103],"0.889,":[105],"respectively;":[106],"macro":[108],"COnPOff":[109,180],"was":[110,141,146,181],"0.685":[111],"(95%":[112],"recording-bootstrap":[113],"interval,":[114],"0.643\u20130.727).":[115],"On":[116],"same":[118],"waveforms":[120],"metrics,":[122],"fixed":[124],"official":[125],"M4Singer-trained":[126],"ROSVOT":[127],"checkpoint":[128],"obtained":[129],"0.171,":[130],"0.230":[131],"0.265":[133],"without":[134],"Molina":[135],"tuning.":[136],"Frame-level":[137],"raw":[138],"accuracy":[140,145,216],"0.882":[142],"overall":[144],"0.761.":[147],"Segmentation":[148],"events":[149,231],"were":[150],"not":[151,212,259],"concentrated":[152],"at":[153],"phrase":[154,165],"boundaries:":[155],"only":[156],"2.4%":[157],"occurred":[158],"150":[160],"ms":[161],"an":[163],"operational":[164],"boundary,":[166],"compared":[167],"14.5%":[169],"expected":[170],"temporal":[172],"coverage.":[173],"In":[174],"native":[176],"zero-shot":[177],"HumTrans":[178],"test,":[179],"0.008;":[182],"separate":[184,287],"validation-aligned":[185],"sensitivity":[186],"analysis":[187],"using":[188],"frozen":[190],"\u20130.18":[191],"s":[192],"shift":[193],"yielded":[194],"0.146.":[195],"Audio-":[196],"note-derived":[198],"pitch-class":[199],"profiles":[200],"showed":[201],"high":[202],"descriptive":[203],"agreement":[204],"(mean":[205],"cosine":[206],"similarity":[207],"0.978),":[208],"this":[210,256],"interpreted":[213],"as":[214],"key-prediction":[215],"independent":[218,272],"key":[219],"labels":[220],"unavailable.":[222],"A":[223],"compact":[224],"boundary":[225],"model":[226],"can":[227],"recover":[228],"useful":[229],"contours":[234],"in":[235],"small-data":[236],"monophonic":[237],"humming,":[238],"provided":[239],"that":[240,255],"parameter":[241],"annotations":[246],"audited.":[248],"large":[250],"internal-to-external":[251],"performance":[252],"drop":[253],"shows":[254],"evidence":[257],"does":[258],"establish":[260],"corpus-independent":[261],"generalisation.":[262],"38-recording":[264],"annotation":[265],"set":[266],"remains":[267],"limiting":[269],"unit":[270],"evidence.":[273],"Remaining":[274],"errors":[275],"occur":[276],"mainly":[277],"continuously":[279],"voiced":[280],"passages,":[281],"tonal":[283],"descriptors":[284],"should":[285],"remain":[286],"hard":[289],"correction.":[291]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2026-10-29T00:00:00"}