{"id":"https://openalex.org/W2089170860","doi":"https://doi.org/10.1109/taslp.2015.2436345","title":"An Acoustic-Phonetic Model of F0 Likelihood for Vocal Melody Extraction","display_name":"An Acoustic-Phonetic Model of F0 Likelihood for Vocal Melody Extraction","publication_year":2015,"publication_date":"2015-05-21","ids":{"openalex":"https://openalex.org/W2089170860","doi":"https://doi.org/10.1109/taslp.2015.2436345","mag":"2089170860"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2015.2436345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2436345","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5008038664","display_name":"Yu-Ren Chien","orcid":"https://orcid.org/0000-0002-2104-3814"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Ren Chien","raw_affiliation_strings":["Academia Sinica, Institute of Information Science, Taipei, Taiwan","Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Institute of Information Science, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Academia Sinica, Institute of Information Science, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Institute of Information Science, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028285867","display_name":"Shyh\u2010Kang Jeng","orcid":"https://orcid.org/0000-0001-8960-9995"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shyh-Kang Jeng","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5685,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66946664,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"23","issue":"9","first_page":"1457","last_page":"1468"},"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":0.9998000264167786,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9976999759674072,"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/loudness","display_name":"Loudness","score":0.859778881072998},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.8529236316680908},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7460108995437622},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.6132130026817322},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5408217906951904},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5337867140769958},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5027737617492676},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.4935985803604126},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3261203169822693}],"concepts":[{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.859778881072998},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.8529236316680908},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7460108995437622},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.6132130026817322},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5408217906951904},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5337867140769958},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5027737617492676},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.4935985803604126},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3261203169822693},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2015.2436345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2436345","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W182265564","https://openalex.org/W573069471","https://openalex.org/W1558306184","https://openalex.org/W1560906834","https://openalex.org/W1976069042","https://openalex.org/W1993427058","https://openalex.org/W2023800933","https://openalex.org/W2035852710","https://openalex.org/W2042105302","https://openalex.org/W2043188492","https://openalex.org/W2057052076","https://openalex.org/W2088959886","https://openalex.org/W2124539664","https://openalex.org/W2125838338","https://openalex.org/W2163468724","https://openalex.org/W2164764235","https://openalex.org/W2166209411","https://openalex.org/W2168103573","https://openalex.org/W2293399065","https://openalex.org/W2294427542","https://openalex.org/W2296724634","https://openalex.org/W2400828047","https://openalex.org/W4232146731","https://openalex.org/W6678626330","https://openalex.org/W6696653561","https://openalex.org/W6697040288","https://openalex.org/W6697058184","https://openalex.org/W6712856371","https://openalex.org/W6912801166"],"related_works":["https://openalex.org/W2118466154","https://openalex.org/W2118371117","https://openalex.org/W1107690805","https://openalex.org/W2623414262","https://openalex.org/W1998721440","https://openalex.org/W2097318409","https://openalex.org/W1995691490","https://openalex.org/W2739662815","https://openalex.org/W4288088492","https://openalex.org/W2982290989"],"abstract_inverted_index":{"This":[0,35,73],"paper":[1],"presents":[2],"a":[3,20,39,44,66,120,196],"novel":[4],"approach":[5,18,160],"to":[6,16,65,103,128,142],"extraction":[7,133],"of":[8,22,38,47,59,69,76,85,93,123,189],"vocal":[9,23,70],"melodies":[10],"from":[11,110,167,180],"accompanied":[12],"singing":[13,144],"recordings.":[14],"Central":[15],"our":[17,159],"is":[19,53,117,134],"model":[21,36,122],"fundamental":[24],"frequency":[25],"(F0)":[26],"likelihood":[27,95,130],"that":[28,107,187],"integrates":[29],"acoustic-phonetic":[30,82],"knowledge":[31],"and":[32,43,101],"real-world":[33],"data.":[34],"consists":[37],"timbral":[40,77,191],"fitness":[41,52,78,192],"score":[42,193],"loudness":[45,91,105,146],"measure":[46],"each":[48,86],"F0":[49,61,83,115,124,152],"candidate.":[50],"Timbral":[51],"measured":[54],"for":[55,195],"the":[56,90,94,111,129,143,150,171,190],"partial":[57],"amplitudes":[58],"an":[60,81],"candidate,":[62],"with":[63],"respect":[64],"small":[67],"set":[68],"timbre":[71,87],"examples.":[72],"F0-specific":[74],"measurement":[75],"depends":[79],"on":[80,163,175],"modification":[84],"example.":[88],"In":[89],"part":[92],"model,":[96],"sinusoids":[97],"are":[98],"detected,":[99],"tracked,":[100],"pruned":[102],"give":[104],"values":[106],"minimize":[108],"interference":[109],"accompaniment.":[112],"A":[113],"final":[114],"estimate":[116],"determined":[118],"by":[119,136,149],"prior":[121],"sequence":[125],"in":[126,158,199],"addition":[127],"model.":[131],"Melody":[132],"completed":[135],"detecting":[137],"voiced":[138],"time":[139],"positions":[140],"according":[141],"voice":[145],"variations":[147],"given":[148],"estimated":[151],"sequence.":[153],"The":[154],"numerical":[155],"parameters":[156],"involved":[157],"were":[161],"optimized":[162],"three":[164],"development":[165,182],"sets":[166,178],"different":[168],"sources":[169],"before":[170],"system":[172],"was":[173],"evaluated":[174],"ten":[176],"test":[177],"separate":[179],"these":[181],"sets.":[183],"Controlled":[184],"experiments":[185],"show":[186],"use":[188],"accounts":[194],"13%":[197],"difference":[198],"overall":[200],"accuracy.":[201]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
