{"id":"https://openalex.org/W2130770109","doi":"https://doi.org/10.1109/tasl.2011.2182510","title":"A Tandem Algorithm for Singing Pitch Extraction and Voice Separation From Music Accompaniment","display_name":"A Tandem Algorithm for Singing Pitch Extraction and Voice Separation From Music Accompaniment","publication_year":2012,"publication_date":"2012-01-04","ids":{"openalex":"https://openalex.org/W2130770109","doi":"https://doi.org/10.1109/tasl.2011.2182510","mag":"2130770109"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2011.2182510","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2182510","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000838826","display_name":"Chao-Ling Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]},{"id":"https://openalex.org/I4210148979","display_name":"MediaTek (Taiwan)","ror":"https://ror.org/05g9jck81","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210148979"]}],"countries":["CN","TW"],"is_corresponding":false,"raw_author_name":"Chao-Ling Hsu","raw_affiliation_strings":["Mediatek, Inc., Hsinchu, Taiwan",", Mediatek Inc., Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mediatek, Inc., Hsinchu, Taiwan","institution_ids":["https://openalex.org/I4210148979"]},{"raw_affiliation_string":", Mediatek Inc., Hsinchu, Taiwan","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering and Center for Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","[Department of Computer Science and Engineering and Center for Cognitive Science, Ohio State University, Columbus, OH, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and Center for Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"[Department of Computer Science and Engineering and Center for Cognitive Science, Ohio State University, Columbus, OH, USA]","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073451247","display_name":"Jyh\u2010Shing Roger Jang","orcid":"https://orcid.org/0000-0002-7319-9095"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jyh-Shing Roger Jang","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan#TAB#","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087874570","display_name":"Ke Hu","orcid":"https://orcid.org/0000-0002-0511-968X"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Hu","raw_affiliation_strings":["Department of Computer Science and Engineering and Center for Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","[Department of Computer Science and Engineering and Center for Cognitive Science, Ohio State University, Columbus, OH, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and Center for Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"[Department of Computer Science and Engineering and Center for Cognitive Science, Ohio State University, Columbus, OH, USA]","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.6299,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":{"value":0.96657849,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"20","issue":"5","first_page":"1482","last_page":"1491"},"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":0.9998999834060669,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9959999918937683,"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/singing","display_name":"Singing","score":0.9536454677581787},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.72252357006073},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.6693882346153259},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6484122276306152},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4239426255226135},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.42126673460006714},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.39451757073402405},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.19680356979370117},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06146696209907532}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9536454677581787},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.72252357006073},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.6693882346153259},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6484122276306152},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4239426255226135},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.42126673460006714},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.39451757073402405},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.19680356979370117},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06146696209907532},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tasl.2011.2182510","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2182510","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:CiteSeerX.psu:10.1.1.368.2455","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.2455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~dwang/papers/HWJH.taslp12.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W27427732","https://openalex.org/W55723365","https://openalex.org/W160800111","https://openalex.org/W218087806","https://openalex.org/W1575829986","https://openalex.org/W1604012244","https://openalex.org/W1964208564","https://openalex.org/W2023800933","https://openalex.org/W2035852710","https://openalex.org/W2044222806","https://openalex.org/W2097191389","https://openalex.org/W2097468589","https://openalex.org/W2099904336","https://openalex.org/W2100772705","https://openalex.org/W2124539664","https://openalex.org/W2125838338","https://openalex.org/W2134096203","https://openalex.org/W2149425615","https://openalex.org/W2150113039","https://openalex.org/W2150593711","https://openalex.org/W2153495844","https://openalex.org/W2159202424","https://openalex.org/W2164282073","https://openalex.org/W2403272360","https://openalex.org/W2561557072","https://openalex.org/W2766736793","https://openalex.org/W4256399001","https://openalex.org/W4285719527","https://openalex.org/W4300402905","https://openalex.org/W6601134270","https://openalex.org/W6602276745","https://openalex.org/W6636121673","https://openalex.org/W6674917984","https://openalex.org/W6713555227"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2003388820","https://openalex.org/W2381526556","https://openalex.org/W1714737510","https://openalex.org/W2018784870","https://openalex.org/W2400828047"],"abstract_inverted_index":{"Singing":[0],"pitch":[1,39,103,122,131,156],"estimation":[2,98],"and":[3,20,40,46,53,64,71,158],"singing":[4,38,43,69,107,121,143,159],"voice":[5,44,70,108,160],"separation":[6],"are":[7,17,50,74],"challenging":[8],"due":[9],"to":[10,56,76,100],"the":[11,37,42,58,83,86,102,118,139,142,149],"presence":[12],"of":[13,85,105,120,129,141],"music":[14],"accompaniments":[15],"that":[16,35,148],"often":[18],"nonstationary":[19],"harmonic.":[21],"Inspired":[22],"by":[23,61,124,135],"computational":[24],"auditory":[25],"scene":[26],"analysis":[27],"(CASA),":[28],"this":[29],"paper":[30],"investigates":[31],"a":[32,96,106,126],"tandem":[33,87,150],"algorithm":[34,88,99,151],"estimates":[36],"separates":[41],"jointly":[45],"iteratively.":[47,80],"Rough":[48],"pitches":[49,73],"first":[51],"estimated":[52,72],"then":[54],"used":[55,75],"separate":[57],"target":[59],"singer":[60],"considering":[62],"harmonicity":[63],"temporal":[65],"continuity.":[66],"The":[67,113],"separated":[68],"improve":[77],"each":[78,110],"other":[79],"To":[81],"enhance":[82],"performance":[84],"for":[89,155],"dealing":[90],"with":[91],"musical":[92,136],"recordings,":[93],"we":[94],"propose":[95],"trend":[97,115],"detect":[101],"ranges":[104],"in":[109],"time":[111],"frame.":[112],"detected":[114],"substantially":[116],"reduces":[117],"difficulty":[119],"detection":[123],"removing":[125],"large":[127],"number":[128],"wrong":[130],"candidates":[132],"either":[133],"produced":[134],"instruments":[137],"or":[138],"overtones":[140],"voice.":[144],"Systematic":[145],"evaluation":[146],"shows":[147],"outperforms":[152],"previous":[153],"systems":[154],"extraction":[157],"separation.":[161]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}