{"id":"https://openalex.org/W1965243342","doi":"https://doi.org/10.1145/2733373.2806257","title":"Towards Solving the Bottleneck of Pitch-based Singing Voice Separation","display_name":"Towards Solving the Bottleneck of Pitch-based Singing Voice Separation","publication_year":2015,"publication_date":"2015-10-13","ids":{"openalex":"https://openalex.org/W1965243342","doi":"https://doi.org/10.1145/2733373.2806257","mag":"1965243342"},"language":"en","primary_location":{"id":"doi:10.1145/2733373.2806257","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2733373.2806257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM international conference on Multimedia","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/A5100934338","display_name":"Bilei Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bilei Zhu","raw_affiliation_strings":["Fudan University, Shanghai, China","Fudan University Shanghai, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University Shanghai, China#TAB#","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318193","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-4486-8341"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["Fudan University, Shanghai, China","Fudan University Shanghai, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University Shanghai, China#TAB#","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100721239","display_name":"Linwei Li","orcid":"https://orcid.org/0000-0002-8406-8322"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linwei Li","raw_affiliation_strings":["Fudan University, Shanghai, China","Fudan University Shanghai, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University Shanghai, China#TAB#","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100934338"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.5744,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66085588,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"511","last_page":"520"},"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8519615530967712},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8201998472213745},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7379323840141296},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.7162840962409973},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7030961513519287},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5603574514389038},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.5439112782478333},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.5274641513824463},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.43282434344291687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3982316255569458},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3542109727859497},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31756824254989624},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.3151371479034424},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.22375133633613586}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8519615530967712},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8201998472213745},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7379323840141296},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.7162840962409973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7030961513519287},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5603574514389038},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.5439112782478333},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.5274641513824463},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43282434344291687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3982316255569458},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3542109727859497},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31756824254989624},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3151371479034424},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.22375133633613586},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2733373.2806257","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2733373.2806257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1482650115","https://openalex.org/W1548802052","https://openalex.org/W1604012244","https://openalex.org/W1902027874","https://openalex.org/W1964208564","https://openalex.org/W1976069042","https://openalex.org/W2002016907","https://openalex.org/W2035852710","https://openalex.org/W2057745663","https://openalex.org/W2098166503","https://openalex.org/W2104298926","https://openalex.org/W2112047474","https://openalex.org/W2120202836","https://openalex.org/W2124232593","https://openalex.org/W2124539664","https://openalex.org/W2130770109","https://openalex.org/W2132597408","https://openalex.org/W2138445519","https://openalex.org/W2148694408","https://openalex.org/W2150415460","https://openalex.org/W2151785180","https://openalex.org/W2152591660","https://openalex.org/W2159898352","https://openalex.org/W2161632835","https://openalex.org/W2164098335","https://openalex.org/W2166209411","https://openalex.org/W2403272360","https://openalex.org/W2561557072","https://openalex.org/W2999905431","https://openalex.org/W3143596294","https://openalex.org/W3216401400","https://openalex.org/W4205778870","https://openalex.org/W4292023222"],"related_works":["https://openalex.org/W2551137307","https://openalex.org/W2100772705","https://openalex.org/W2113526703","https://openalex.org/W2123043102","https://openalex.org/W2577807713","https://openalex.org/W3094316140","https://openalex.org/W3133205200","https://openalex.org/W2547262076","https://openalex.org/W2098101267","https://openalex.org/W2103031592"],"abstract_inverted_index":{"Singing":[0],"voice":[1,116],"separation":[2,59,197],"from":[3],"accompaniment":[4],"in":[5,13,86],"monaural":[6],"music":[7,14],"recordings":[8],"is":[9,117,128],"a":[10,49],"crucial":[11],"technique":[12],"information":[15],"retrieval.":[16],"A":[17],"majority":[18],"of":[19,43,61,71,98,124,171,184],"existing":[20],"algorithms":[21,63],"are":[22,84,111,166,186],"based":[23,78],"on":[24,79,176],"singing":[25,45,115,196],"pitch":[26,32,55,126,154],"detection,":[27],"and":[28,38,113,142,189],"take":[29],"the":[30,34,40,44,58,68,95,114,122,138,153,158,169,177,190],"detected":[31],"as":[33,48,149],"cue":[35,151],"to":[36,136,155],"identify":[37,157],"separate":[39],"harmonic":[41,160],"structure":[42],"voice.":[46],"However,":[47],"key":[50],"yet":[51],"undependable":[52],"premise,":[53],"vocal":[54,108,125,159],"detection":[56,127],"makes":[57],"performance":[60],"these":[62],"rather":[64,187],"limited.":[65],"To":[66],"overcome":[67],"inherent":[69],"weakness":[70],"pitch-based":[72,172],"inference":[73],"algorithms,":[74],"two":[75,163],"novel":[76],"methods":[77,165],"non-negative":[80],"matrix":[81],"factorization":[82],"(NMF)":[83],"devised":[85],"this":[87],"paper.":[88],"The":[89,131,162],"first":[90],"one":[91],"combines":[92],"NMF":[93,135],"with":[94],"distribution":[96],"regularities":[97],"vocals":[99],"under":[100],"different":[101],"time":[102],"frequency":[103],"resolutions,":[104],"so":[105],"that":[106,182],"many":[107],"unrelated":[109],"portions":[110],"eliminated":[112],"hence":[118],"enhanced.":[119],"In":[120],"consequence,":[121],"accuracy":[123],"significantly":[129],"improved.":[130],"second":[132],"method":[133],"applies":[134],"decompose":[137],"spectrogram":[139],"into":[140,168],"non-overlapping":[141],"indivisible":[143],"segments,":[144],"which":[145],"can":[146],"be":[147],"used":[148],"another":[150],"besides":[152],"help":[156],"structure.":[161],"proposed":[164],"integrated":[167],"framework":[170],"inference.":[173],"Extensive":[174],"testing":[175],"MIR-1K":[178],"public":[179],"dataset":[180],"shows":[181],"both":[183],"them":[185],"effective,":[188],"overall":[191],"performances":[192],"outperform":[193],"other":[194],"state-of-the-art":[195],"algorithms.":[198]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}