{"id":"https://openalex.org/W3162013464","doi":"https://doi.org/10.1109/icassp39728.2021.9414190","title":"Singing Melody Extraction from Polyphonic Music based on Spectral Correlation Modeling","display_name":"Singing Melody Extraction from Polyphonic Music based on Spectral Correlation Modeling","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162013464","doi":"https://doi.org/10.1109/icassp39728.2021.9414190","mag":"3162013464"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414190","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5091528537","display_name":"Xingjian Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingjian Du","raw_affiliation_strings":["Bytedance AI Lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100934338","display_name":"Bilei Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bilei Zhu","raw_affiliation_strings":["Bytedance AI Lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiuqiang Kong","raw_affiliation_strings":["Bytedance AI Lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110851569","display_name":"Zejun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejun Ma","raw_affiliation_strings":["Bytedance AI Lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5439,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.60035892,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"241","last_page":"245"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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":0.996399998664856,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.8811613321304321},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7721585631370544},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6664787530899048},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6423794627189636},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6028379201889038},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.601626455783844},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5580501556396484},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5282009243965149},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5226930379867554},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5182356834411621},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5100591778755188},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5097300410270691},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.494172602891922},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12413045763969421},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09959954023361206}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8811613321304321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7721585631370544},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6664787530899048},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6423794627189636},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6028379201889038},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.601626455783844},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5580501556396484},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5282009243965149},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5226930379867554},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5182356834411621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5100591778755188},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5097300410270691},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.494172602891922},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12413045763969421},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09959954023361206},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414190","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1607142029","https://openalex.org/W1976069042","https://openalex.org/W2161632835","https://openalex.org/W2296724634","https://openalex.org/W2773294482","https://openalex.org/W2811135961","https://openalex.org/W2920728711","https://openalex.org/W2932319787","https://openalex.org/W2963314703","https://openalex.org/W2963446712","https://openalex.org/W2963535133","https://openalex.org/W2963623257","https://openalex.org/W2964177567","https://openalex.org/W2968917279","https://openalex.org/W2969937244","https://openalex.org/W2994689640","https://openalex.org/W3049401840","https://openalex.org/W3150201805","https://openalex.org/W6636203886","https://openalex.org/W6697040288","https://openalex.org/W6746836464","https://openalex.org/W6753055032","https://openalex.org/W6753441378","https://openalex.org/W6760299066","https://openalex.org/W6766837696","https://openalex.org/W6767164110","https://openalex.org/W6782211628"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2371528275","https://openalex.org/W2375454309","https://openalex.org/W2374135200","https://openalex.org/W2390487542"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"network":[2],"(CNN)":[3],"based":[4],"methods":[5,21],"have":[6],"achieved":[7],"state-of-the-art":[8,128],"performance":[9],"for":[10,52],"singing":[11],"melody":[12,53],"extraction":[13],"from":[14],"polyphonic":[15],"music.":[16],"However,":[17],"most":[18],"of":[19,26,47,82,102,114,121,131],"these":[20],"focus":[22],"on":[23,133],"the":[24,45,68,80,98,106,119,134],"learning":[25],"local":[27],"features,":[28],"while":[29],"relationships":[30,69],"among":[31,70],"spectral":[32,49,59,84],"components":[33],"locating":[34],"far":[35],"apart":[36],"are":[37],"often":[38],"neglected.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43,56,91],"explore":[44],"idea":[46],"modeling":[48],"correlation":[50,60],"explicitly":[51],"extraction.":[54],"Specifically,":[55],"present":[57],"a":[58,75,87,110,127],"module":[61],"(SCM)":[62],"that":[63],"can":[64],"learn":[65],"to":[66,93,104,117],"model":[67,112],"all":[71],"frequency":[72],"bands":[73],"in":[74],"time-frequency":[76],"representation,":[77],"thus":[78],"allowing":[79],"encoding":[81],"global":[83],"information":[85],"into":[86],"conventional":[88],"CNN.":[89],"Furthermore,":[90],"propose":[92],"integrate":[94],"center":[95],"frequencies":[96],"with":[97],"input":[99],"feature":[100],"map":[101],"SCM":[103,115],"improve":[105],"performance.":[107],"We":[108],"implement":[109],"light-weight":[111],"comprised":[113],"blocks":[116],"verify":[118],"efficacy":[120],"our":[122],"system.":[123],"Our":[124],"system":[125],"achieves":[126],"overall":[129],"accuracy":[130],"83.5%":[132],"MedleyDB":[135],"dataset.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}