{"id":"https://openalex.org/W2065495703","doi":"https://doi.org/10.1109/taslp.2013.2285484","title":"Multi-pitch Streaming of Harmonic Sound Mixtures","display_name":"Multi-pitch Streaming of Harmonic Sound Mixtures","publication_year":2013,"publication_date":"2013-12-04","ids":{"openalex":"https://openalex.org/W2065495703","doi":"https://doi.org/10.1109/taslp.2013.2285484","mag":"2065495703"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2013.2285484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2013.2285484","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/A5102749436","display_name":"Zhiyao Duan","orcid":"https://orcid.org/0000-0002-8334-9974"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhiyao Duan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY","Dept. of Electr. & Comput. Eng., Univ. of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Univ. of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102341476","display_name":"Jinyu Han","orcid":"https://orcid.org/0009-0005-8484-8889"},"institutions":[{"id":"https://openalex.org/I169912796","display_name":"Grace (United States)","ror":"https://ror.org/03k4vk194","country_code":"US","type":"company","lineage":["https://openalex.org/I169912796"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Han","raw_affiliation_strings":["Gracenote, Oakland, California, United States","Gracenote, Emeryville, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Gracenote, Oakland, California, United States","institution_ids":["https://openalex.org/I169912796"]},{"raw_affiliation_string":"Gracenote, Emeryville, CA, USA#TAB#","institution_ids":["https://openalex.org/I169912796"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102878078","display_name":"Bryan Pardo","orcid":"https://orcid.org/0000-0002-1427-6492"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan Pardo","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Northwestern University, Evanston, IL, United States","Dept. of Electr. Eng. and Comput. Sci., Northwestern Univ., Evanston, IL, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Northwestern University, Evanston, IL, United States","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Dept. of Electr. Eng. and Comput. Sci., Northwestern Univ., Evanston, IL, USA#TAB#","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102749436"],"corresponding_institution_ids":["https://openalex.org/I5388228"],"apc_list":null,"apc_paid":null,"fwci":3.5372,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.93121937,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"22","issue":"1","first_page":"138","last_page":"150"},"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":0.9997000098228455,"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":0.9983999729156494,"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/timbre","display_name":"Timbre","score":0.895982027053833},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7389265298843384},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7005171775817871},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6397428512573242},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6233549118041992},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.618092954158783},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.5212860107421875},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48753735423088074},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4615184962749481},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2655380964279175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25223129987716675},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.18664312362670898}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.895982027053833},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7389265298843384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7005171775817871},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6397428512573242},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6233549118041992},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.618092954158783},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.5212860107421875},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48753735423088074},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4615184962749481},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2655380964279175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25223129987716675},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.18664312362670898},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2013.2285484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2013.2285484","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.725.9579","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.725.9579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.rochester.edu/%7Ezduan/resource/DuanHanPardo_MultiPitchStreaming_TASLP.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.737.3915","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.737.3915","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://music.cs.northwestern.edu/publications/DuanHanPardo_MPS_TASLP13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W108716120","https://openalex.org/W129413713","https://openalex.org/W173783047","https://openalex.org/W196347269","https://openalex.org/W361149621","https://openalex.org/W1529007784","https://openalex.org/W1875231349","https://openalex.org/W1881757884","https://openalex.org/W1964538581","https://openalex.org/W1974196562","https://openalex.org/W1984544290","https://openalex.org/W1991139021","https://openalex.org/W2005503476","https://openalex.org/W2023800933","https://openalex.org/W2054770976","https://openalex.org/W2060822897","https://openalex.org/W2062078328","https://openalex.org/W2067265757","https://openalex.org/W2078887028","https://openalex.org/W2088361146","https://openalex.org/W2088832111","https://openalex.org/W2091425152","https://openalex.org/W2104112890","https://openalex.org/W2107328928","https://openalex.org/W2109252613","https://openalex.org/W2110644015","https://openalex.org/W2113217465","https://openalex.org/W2113475414","https://openalex.org/W2115129089","https://openalex.org/W2115202071","https://openalex.org/W2115657355","https://openalex.org/W2118740006","https://openalex.org/W2119599673","https://openalex.org/W2125722442","https://openalex.org/W2130768851","https://openalex.org/W2134089414","https://openalex.org/W2136833314","https://openalex.org/W2139318943","https://openalex.org/W2143341575","https://openalex.org/W2144414181","https://openalex.org/W2145678789","https://openalex.org/W2145905122","https://openalex.org/W2149095746","https://openalex.org/W2150286575","https://openalex.org/W2157313348","https://openalex.org/W2159202424","https://openalex.org/W2161855744","https://openalex.org/W2164764235","https://openalex.org/W2403891086","https://openalex.org/W3127686677","https://openalex.org/W4256399001","https://openalex.org/W6604371994","https://openalex.org/W6607058411","https://openalex.org/W6607961521","https://openalex.org/W6633328910","https://openalex.org/W6639350448","https://openalex.org/W6676956424","https://openalex.org/W6679849079","https://openalex.org/W6681658821","https://openalex.org/W6682017866","https://openalex.org/W6683973074","https://openalex.org/W6917638038"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2787035864","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2160511961"],"abstract_inverted_index":{"Multi-pitch":[0],"analysis":[1],"of":[2,17,32,77,161],"concurrent":[3],"sound":[4,45],"sources":[5,20],"is":[6,103,151],"an":[7],"important":[8],"but":[9],"challenging":[10],"problem.":[11],"It":[12],"requires":[13],"estimating":[14],"pitch":[15,27,54,66,162],"values":[16],"all":[18],"harmonic":[19,123],"in":[21],"individual":[22],"frames":[23],"and":[24,63,119,125,142,197],"streaming":[25,41,200],"the":[26,40,49,86,106,185,190],"estimates":[28,55,163],"into":[29],"trajectories,":[30],"each":[31,69,94,110],"which":[33],"corresponds":[34,96],"to":[35,97,104,165],"a":[36,65,89,98,126,171],"source.":[37,70,99],"We":[38,47,112,146,169,188],"address":[39],"problem":[42,87],"for":[43,68,117,139,153,206],"monophonic":[44],"sources.":[46],"take":[48],"original":[50],"audio,":[51],"plus":[52],"frame-level":[53],"from":[56,80],"any":[57],"multi-pitch":[58,199],"estimation":[59],"algorithm":[60,175],"as":[61,88,178,181],"inputs,":[62],"output":[64],"trajectory":[67],"Our":[71],"approach":[72,192],"does":[73],"not":[74],"require":[75],"pre-training":[76],"source":[78],"models":[79],"isolated":[81],"recordings.":[82],"Instead,":[83],"it":[84],"casts":[85],"constrained":[90,173],"clustering":[91,101,174,186],"problem,":[92],"where":[93],"cluster":[95],"The":[100],"objective":[102],"minimize":[105],"timbre":[107,115],"inconsistency":[108],"within":[109],"cluster.":[111],"explore":[113],"different":[114],"features":[116],"music":[118,207],"speech.":[120,209],"For":[121],"music,":[122],"structure":[124],"newly":[127],"proposed":[128,191],"feature":[129],"called":[130],"uniform":[131],"discrete":[132],"cepstrum":[133],"(UDC)":[134],"are":[135,157,203,214],"found":[136],"effective;":[137],"while":[138,183],"speech,":[140],"MFCC":[141],"UDC":[143],"works":[144],"well.":[145],"also":[147],"show":[148],"that":[149,176,202],"timbre-consistency":[150],"insufficient":[152],"effective":[154],"streaming.":[155],"Constraints":[156],"imposed":[158],"on":[159],"pairs":[160],"according":[164],"their":[166],"time-frequency":[167],"relationships.":[168],"propose":[170],"new":[172],"satisfies":[177],"many":[179],"constraints":[180],"possible":[182],"optimizing":[184],"objective.":[187],"compare":[189],"with":[193],"other":[194],"state-of-the-art":[195],"supervised":[196],"unsupervised":[198],"approaches":[201],"specifically":[204],"designed":[205],"or":[208,211],"Better":[210],"comparable":[212],"results":[213],"shown.":[215]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}