{"id":"https://openalex.org/W4405632977","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800383","title":"Singer Separation for Karaoke Content Generation","display_name":"Singer Separation for Karaoke Content Generation","publication_year":2024,"publication_date":"2024-10-17","ids":{"openalex":"https://openalex.org/W4405632977","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800383"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda64382.2024.10800383","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800383","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103538758","display_name":"Hsuan-Yu Lin","orcid":"https://orcid.org/0009-0004-6516-3692"},"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":"Hsuan-Yu Lin","raw_affiliation_strings":["Graduate Institute of Networking and Multimedia, National Taiwan University,Taipei,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Networking and Multimedia, National Taiwan University,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051463746","display_name":"Xuanjun Chen","orcid":null},"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":"Xuanjun Chen","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"]}]},{"author_position":"last","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/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":"Jyh-Shing Roger Jang","raw_affiliation_strings":["National Taiwan University,Dept. of Computer Science and Information Engineering,Taipei,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Dept. of Computer Science and Information Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2897158,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9940999746322632,"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":0.9940999746322632,"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":0.9940000176429749,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9819999933242798,"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/computer-science","display_name":"Computer science","score":0.5356561541557312},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4548845589160919},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.0428767204284668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5356561541557312},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4548845589160919},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0428767204284668}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda64382.2024.10800383","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800383","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2047504078","https://openalex.org/W2127851351","https://openalex.org/W2128653836","https://openalex.org/W2962866891","https://openalex.org/W2962935966","https://openalex.org/W2964058413","https://openalex.org/W3015199127","https://openalex.org/W3096893582","https://openalex.org/W6751512325"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2071676784","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Due":[0],"to":[1,53,85,120,144,165],"the":[2,42,55,72,109,128,146,176],"rapid":[3],"development":[4],"of":[5,44,148],"deep":[6],"learning,":[7],"we":[8,51,80,104,172],"can":[9,22,161],"now":[10],"successfully":[11],"separate":[12,54],"singing":[13],"voice":[14],"from":[15,27,71],"mono":[16],"audio":[17],"music.":[18],"However,":[19],"this":[20,48,78,83,149,174],"separation":[21,43,89,111,153],"only":[23,40],"extract":[24,66],"human":[25],"voices":[26],"other":[28],"musical":[29],"instruments,":[30],"which":[31,91,139],"is":[32,154,175],"undesirable":[33],"for":[34,95,108,157,180],"karaoke":[35,49,93,166,182],"content":[36,94,167],"generation":[37],"applications":[38],"that":[39],"require":[41],"lead":[45,69,100,124],"singers.":[46,101],"For":[47,77],"application,":[50],"need":[52],"music":[56,73],"containing":[57,74],"male":[58],"and":[59,113,160],"female":[60],"duets":[61],"into":[62],"two":[63,98],"vocals,":[64],"or":[65,97],"a":[67,87,133],"single":[68],"vocal":[70,75],"harmony.":[76],"reason,":[79],"propose":[81],"in":[82,127],"article":[84],"use":[86],"singer":[88,110,152],"system,":[90],"generates":[92],"one":[96],"separated":[99],"In":[102],"particular,":[103],"introduced":[105],"three":[106],"models":[107],"task":[112],"designed":[114],"an":[115],"automatic":[116],"model":[117],"selection":[118],"scheme":[119],"distinguish":[121],"how":[122],"many":[123],"singers":[125],"are":[126],"song.":[129],"We":[130],"also":[131],"collected":[132],"large":[134],"enough":[135],"data":[136],"set,":[137],"MIR-SingerSeparation11https://gulaerchen.github.io/MIR-SingerSeparation/,":[138],"has":[140],"been":[141],"publicly":[142],"released":[143],"advance":[145],"frontier":[147],"research.":[150],"Our":[151],"most":[155],"suitable":[156],"sentimental":[158],"ballads":[159],"be":[162],"directly":[163],"applied":[164],"generation.":[168],"As":[169],"far":[170],"as":[171],"know,":[173],"first":[177],"singer-separation":[178],"work":[179],"real-world":[181],"applications.":[183]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}