{"id":"https://openalex.org/W2955176369","doi":"https://doi.org/10.1145/3330393.3330400","title":"Melody extraction from polyphonic music based on the amplitude relation","display_name":"Melody extraction from polyphonic music based on the amplitude relation","publication_year":2019,"publication_date":"2019-05-10","ids":{"openalex":"https://openalex.org/W2955176369","doi":"https://doi.org/10.1145/3330393.3330400","mag":"2955176369"},"language":"en","primary_location":{"id":"doi:10.1145/3330393.3330400","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3330393.3330400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 4th International Conference on Multimedia Systems and Signal Processing","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/A5101555145","display_name":"Yajun Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yajun Liang","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369793","display_name":"Chen Li","orcid":"https://orcid.org/0000-0002-0079-3106"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Li","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100777340","display_name":"Lihua Tian","orcid":"https://orcid.org/0000-0002-7206-4332"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lihua Tian","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101555145"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.1659,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43058795,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"84","last_page":"88"},"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":0.9983999729156494,"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":0.9916999936103821,"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/amplitude","display_name":"Amplitude","score":0.6661021709442139},{"id":"https://openalex.org/keywords/salience","display_name":"Salience (neuroscience)","score":0.5964519381523132},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.5663930773735046},{"id":"https://openalex.org/keywords/loudness","display_name":"Loudness","score":0.555649995803833},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.5540543794631958},{"id":"https://openalex.org/keywords/harmonics","display_name":"Harmonics","score":0.5527693629264832},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5259944200515747},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.5038802027702332},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.4842259883880615},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4761916697025299},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4623417258262634},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.4279963970184326},{"id":"https://openalex.org/keywords/amplitude-modulation","display_name":"Amplitude modulation","score":0.41199105978012085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3520806133747101},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.2961399555206299},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2924216389656067},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.28368276357650757},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.24067366123199463},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1357240080833435},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.12666848301887512},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.11360183358192444},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08978283405303955}],"concepts":[{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.6661021709442139},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.5964519381523132},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.5663930773735046},{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.555649995803833},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5540543794631958},{"id":"https://openalex.org/C188414643","wikidata":"https://www.wikidata.org/wiki/Q3001183","display_name":"Harmonics","level":3,"score":0.5527693629264832},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5259944200515747},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.5038802027702332},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.4842259883880615},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4761916697025299},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4623417258262634},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.4279963970184326},{"id":"https://openalex.org/C201905106","wikidata":"https://www.wikidata.org/wiki/Q183755","display_name":"Amplitude modulation","level":4,"score":0.41199105978012085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3520806133747101},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.2961399555206299},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2924216389656067},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.28368276357650757},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.24067366123199463},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1357240080833435},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.12666848301887512},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.11360183358192444},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08978283405303955},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3330393.3330400","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3330393.3330400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 4th International Conference on Multimedia Systems and Signal Processing","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":12,"referenced_works":["https://openalex.org/W206353804","https://openalex.org/W1497705940","https://openalex.org/W1976069042","https://openalex.org/W2023800933","https://openalex.org/W2089170860","https://openalex.org/W2161632835","https://openalex.org/W2166209411","https://openalex.org/W2168103573","https://openalex.org/W2397569413","https://openalex.org/W2556247670","https://openalex.org/W2902480954","https://openalex.org/W4235716345"],"related_works":["https://openalex.org/W2118466154","https://openalex.org/W2118371117","https://openalex.org/W2464878701","https://openalex.org/W4247380401","https://openalex.org/W3013946943","https://openalex.org/W1971741040","https://openalex.org/W2291406444","https://openalex.org/W2131493640","https://openalex.org/W2078310833","https://openalex.org/W2162957703"],"abstract_inverted_index":{"Most":[0],"of":[1,12,21,32,49,95,117,120,132,150,184,190,212],"the":[2,9,13,18,22,29,47,50,56,67,79,82,89,115,118,124,146,154,157,160,163,167,170,182,188,191,198,205,209,213,216,219,228,246,252],"melody":[3,33,42,230,254],"extraction":[4,34,43],"methods":[5],"only":[6],"focus":[7],"on":[8,46,114],"temporal":[10,19],"continuity":[11],"frequency,":[14],"and":[15,81,91,123,148,166,196,208,223,227],"seldom":[16],"consider":[17],"correlation":[20,48,116],"frequency":[23,51,69,90,98,134,139],"amplitude,":[24],"which":[25],"would":[26],"result":[27],"in":[28,55,71,178,193],"poor":[30],"effect":[31],"for":[35,175,203],"many":[36],"algorithms.":[37],"Consequently,":[38],"a":[39,109,130],"new":[40,110],"main":[41,229,253],"method":[44,248],"based":[45,113],"amplitude":[52,165,192,202,224],"is":[53,63,75,85,127,231,235],"proposed":[54,247],"paper.":[57],"Firstly,":[58],"an":[59],"equal":[60],"loudness":[61],"filter":[62],"used":[64,76,86],"to":[65,77,87],"enhance":[66],"ear-sensitive":[68],"band":[70],"music.":[72,257],"The":[73,241],"STFT":[74],"convert":[78],"spectrum":[80],"phase":[83],"vocoder":[84],"correct":[88],"amplitude.":[92],"Then,":[93],"lots":[94],"most":[96,171],"salience":[97,111,222],"points":[99,140],"near":[100],"spectral":[101],"peaks":[102],"are":[103,141,173,225],"selected":[104,174],"as":[105],"pitch":[106,126,155,161,168],"candidates":[107],"by":[108,129,144],"function":[112],"amplitudes":[119],"adjacent":[121],"frames,":[122],"perceived":[125],"reverse-reasoned":[128],"pair":[131],"high":[133],"points.":[135],"Some":[136],"pseudo":[137],"fundamental":[138],"filtered":[142],"out":[143],"detecting":[145],"number":[147],"distribution":[149,189],"their":[151],"harmonics.":[152],"Next,":[153],"with":[156,162,169,200,218],"greatest":[158,164],"salience,":[159],"harmonics":[172],"creating":[176],"contours":[177,217],"each":[179,194],"frame.":[180],"After":[181],"creation":[183],"contour,":[185],"we":[186],"analyze":[187],"contour":[195,239],"clip":[197],"fragments":[199],"smaller":[201,220],"determining":[204],"start":[206],"point":[207,211],"end":[210],"melody.":[214],"Finally,":[215],"mean":[221],"removed":[226],"identified":[232],"when":[233],"there":[234],"more":[236],"than":[237],"one":[238],"simultaneously.":[240],"experimental":[242],"results":[243],"show":[244],"that":[245],"can":[249],"effectively":[250],"extract":[251],"from":[255],"polyphonic":[256]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}