{"id":"https://openalex.org/W2166209411","doi":"https://doi.org/10.1109/tasl.2010.2041114","title":"Source/Filter Model for Unsupervised Main Melody Extraction From Polyphonic Audio Signals","display_name":"Source/Filter Model for Unsupervised Main Melody Extraction From Polyphonic Audio Signals","publication_year":2010,"publication_date":"2010-02-16","ids":{"openalex":"https://openalex.org/W2166209411","doi":"https://doi.org/10.1109/tasl.2010.2041114","mag":"2166209411"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2010.2041114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2041114","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/163304","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080804613","display_name":"Jean-Louis Durrieu","orcid":null},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Louis Durrieu","raw_affiliation_strings":["TELECOM ParisTech CNRS LTCI-46, Institut TELECOM, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TELECOM ParisTech CNRS LTCI-46, Institut TELECOM, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I1294671590","https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112054021","display_name":"Ga\u00ebl Richard","orcid":null},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ga\u00ebl Richard","raw_affiliation_strings":["TELECOM ParisTech CNRS LTCI-46, Institut TELECOM, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TELECOM ParisTech CNRS LTCI-46, Institut TELECOM, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I1294671590","https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101029000","display_name":"Bertrand David","orcid":null},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Bertrand David","raw_affiliation_strings":["TELECOM ParisTech CNRS LTCI-46, Institut TELECOM, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TELECOM ParisTech CNRS LTCI-46, Institut TELECOM, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I1294671590","https://openalex.org/I4210165912"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022368934","display_name":"C\u00e9dric F\u00e9votte","orcid":"https://orcid.org/0000-0003-3801-5534"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"C\u00e9dric Fevotte","raw_affiliation_strings":["TELECOM ParisTech-46, CNRS LTCI, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TELECOM ParisTech-46, CNRS LTCI, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I1294671590","https://openalex.org/I4210165912"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":15.9796,"has_fulltext":false,"cited_by_count":155,"citation_normalized_percentile":{"value":0.9946396,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"18","issue":"3","first_page":"564","last_page":"575"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9937999844551086,"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/computer-science","display_name":"Computer science","score":0.7829511165618896},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.709263026714325},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.6364956498146057},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6139842867851257},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5969570875167847},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.531532347202301},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.49008262157440186},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4766874313354492},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.45906901359558105},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4511772692203522},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44336646795272827},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43526285886764526},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.43020230531692505},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.43007466197013855},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.20329585671424866},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12623000144958496},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1090487539768219}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7829511165618896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.709263026714325},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.6364956498146057},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6139842867851257},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5969570875167847},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.531532347202301},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.49008262157440186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4766874313354492},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.45906901359558105},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4511772692203522},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44336646795272827},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43526285886764526},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.43020230531692505},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.43007466197013855},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.20329585671424866},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12623000144958496},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1090487539768219},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tasl.2010.2041114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2041114","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:infoscience.epfl.ch:163304","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/163304","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.tind.io:163304","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/64167","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"research article"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:163304","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/163304","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W121807565","https://openalex.org/W178932670","https://openalex.org/W181056519","https://openalex.org/W281680360","https://openalex.org/W1521419984","https://openalex.org/W1958993123","https://openalex.org/W2022194925","https://openalex.org/W2039844283","https://openalex.org/W2049633694","https://openalex.org/W2099904336","https://openalex.org/W2103031592","https://openalex.org/W2127851351","https://openalex.org/W2132597408","https://openalex.org/W2134807719","https://openalex.org/W2135029798","https://openalex.org/W2137319814","https://openalex.org/W2142669986","https://openalex.org/W2150113039","https://openalex.org/W2150415460","https://openalex.org/W2168103573","https://openalex.org/W2290894215","https://openalex.org/W2303258217","https://openalex.org/W2403272360","https://openalex.org/W2407544556","https://openalex.org/W2734907090","https://openalex.org/W2915553788","https://openalex.org/W4206319965","https://openalex.org/W6604915701","https://openalex.org/W6631211390","https://openalex.org/W6640989775","https://openalex.org/W6680012447","https://openalex.org/W6696335493","https://openalex.org/W6698319557","https://openalex.org/W6698442552","https://openalex.org/W6713555227","https://openalex.org/W6714162195","https://openalex.org/W6740636266"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W3132176577","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W2114974607","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W3112881379","https://openalex.org/W2002298560","https://openalex.org/W2019256813"],"abstract_inverted_index":{"Extracting":[0],"the":[1,24,30,54,59,65,83,101,123,126,151,165],"main":[2,60],"melody":[3,61],"from":[4,69,136,150],"a":[5,17,36,50,78,91,107,132,158],"polyphonic":[6,70],"music":[7],"recording":[8],"seems":[9],"natural":[10],"even":[11],"to":[12,23,41],"untrained":[13],"human":[14,31],"listeners.":[15],"To":[16,73],"certain":[18],"extent":[19],"it":[20],"is":[21,87,98,129,147],"related":[22],"concept":[25],"of":[26,33,58,103,125,144],"source":[27,38,138],"separation,":[28],"with":[29],"ability":[32],"focusing":[34],"on":[35,175],"specific":[37,92],"in":[39,63,100,157],"order":[40],"extract":[42],"relevant":[43],"information.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,76],"propose":[49,77],"new":[51,79],"approach":[52],"for":[53],"estimation":[55,124],"and":[56,113,171],"extraction":[57],"(and":[62],"particular":[64],"leading":[66,84],"vocal":[67,85],"part)":[68],"audio":[71],"signals.":[72],"that":[74,164],"aim,":[75],"signal":[80],"model":[81],"where":[82],"part":[86],"explicitly":[88],"represented":[89],"by":[90],"source/filter":[93],"model.":[94],"The":[95,141,154],"proposed":[96,166],"representation":[97],"investigated":[99],"framework":[102,134],"two":[104],"statistical":[105],"models:":[106],"Gaussian":[108],"Scaled":[109],"Mixture":[110,117],"Model":[111,118],"(GSMM)":[112],"an":[114],"extended":[115],"Instantaneous":[116],"(IMM).":[119],"For":[120],"both":[121],"models,":[122],"different":[127],"parameters":[128],"done":[130],"within":[131],"maximum-likelihood":[133],"adapted":[135],"single-channel":[137],"separation":[139],"techniques.":[140],"desired":[142],"sequence":[143],"fundamental":[145],"frequencies":[146],"then":[148],"inferred":[149],"estimated":[152],"parameters.":[153],"results":[155],"obtained":[156],"recent":[159],"evaluation":[160],"campaign":[161],"(MIREX08)":[162],"show":[163],"approaches":[167],"are":[168],"very":[169],"promising":[170],"reach":[172],"state-of-the-art":[173],"performances":[174],"all":[176],"test":[177],"sets.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":18},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":16}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
