{"id":"https://openalex.org/W2169410099","doi":"https://doi.org/10.1109/icme.2010.5583066","title":"Popular singer identification based on cepstrum transformation","display_name":"Popular singer identification based on cepstrum transformation","publication_year":2010,"publication_date":"2010-07-01","ids":{"openalex":"https://openalex.org/W2169410099","doi":"https://doi.org/10.1109/icme.2010.5583066","mag":"2169410099"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2010.5583066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2010.5583066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Multimedia and Expo","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/A5020303183","display_name":"Wei-Ho Tsai","orcid":"https://orcid.org/0000-0002-0867-7951"},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Wei-Ho Tsai","raw_affiliation_strings":["Department of Electronic Engineering & Graduate Institute of Computer and Communication Engineering, National Taipei University of Technology, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering & Graduate Institute of Computer and Communication Engineering, National Taipei University of Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I118292597"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002686731","display_name":"Hao-Ping Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hao-Ping Lin","raw_affiliation_strings":["Department of Electronic Engineering & Graduate Institute of Computer and Communication Engineering, National Taipei University of Technology, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering & Graduate Institute of Computer and Communication Engineering, National Taipei University of Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I118292597"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020303183"],"corresponding_institution_ids":["https://openalex.org/I118292597"],"apc_list":null,"apc_paid":null,"fwci":1.0115,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.77942035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"584","last_page":"589"},"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":0.9991000294685364,"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":0.9984999895095825,"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":0.8831183314323425},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.848099946975708},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7592970132827759},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.6593162417411804},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6492705345153809},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6440125703811646},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6124026775360107},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5980412364006042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45460882782936096},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.4276595413684845},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4041225016117096},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36636388301849365},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2797931432723999},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09011366963386536}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8831183314323425},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.848099946975708},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7592970132827759},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.6593162417411804},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6492705345153809},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6440125703811646},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6124026775360107},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5980412364006042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45460882782936096},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.4276595413684845},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4041225016117096},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36636388301849365},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2797931432723999},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09011366963386536},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2010.5583066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2010.5583066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W153815065","https://openalex.org/W178884067","https://openalex.org/W190054064","https://openalex.org/W1570504315","https://openalex.org/W1972101987","https://openalex.org/W2015276542","https://openalex.org/W2045724592","https://openalex.org/W2049633694","https://openalex.org/W2107252339","https://openalex.org/W2107990538","https://openalex.org/W2128117472","https://openalex.org/W2128980425","https://openalex.org/W2135567392","https://openalex.org/W2150574373","https://openalex.org/W2154591323","https://openalex.org/W2156063339","https://openalex.org/W2156142001","https://openalex.org/W2165880886","https://openalex.org/W2174404816","https://openalex.org/W2394955069","https://openalex.org/W3129711340","https://openalex.org/W4241682286","https://openalex.org/W4249230140","https://openalex.org/W6606268758","https://openalex.org/W6607294247","https://openalex.org/W6634309418","https://openalex.org/W6682858819","https://openalex.org/W6712099778"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W4317383455","https://openalex.org/W2548511587"],"abstract_inverted_index":{"A":[0],"prerequisite":[1],"for":[2,33],"identifying":[3],"the":[4,13,22,39,73,82,119,133],"singers":[5],"in":[6,49],"popular":[7],"music":[8,30,129],"recordings":[9],"is":[10,93,102],"to":[11,20,103],"reduce":[12],"interference":[14],"of":[15,63,85],"background":[16,29,128],"accompaniment":[17],"when":[18],"trying":[19],"characterize":[21],"singer":[23,34],"voice.":[24],"This":[25,79],"study":[26],"proposes":[27],"a":[28,56,60,86,114,127],"removal":[31,130],"approach":[32,131],"identification":[35],"(SID)":[36],"by":[37,55,67,106],"exploiting":[38],"underlying":[40],"relationships":[41,52],"between":[42],"solo":[43,70],"voices":[44],"and":[45,90],"their":[46],"accompanied":[47,64,100],"versions":[48],"cepstrum.":[50],"The":[51],"are":[53],"characterized":[54],"transformation":[57,80],"estimated":[58],"using":[59],"large":[61],"set":[62],"singing":[65,71,87],"generated":[66],"manually":[68],"mixing":[69],"with":[72,95],"accompaniments":[74],"extracted":[75],"from":[76],"Karaoke":[77],"VCD.":[78],"reflects":[81],"cepstrum":[83,112],"variations":[84],"voice":[88,101],"before":[89],"after":[91],"it":[92],"added":[94],"accompaniments.":[96],"When":[97],"an":[98],"unknown":[99],"be":[104],"identified":[105],"our":[107],"system,":[108],"we":[109],"convert":[110],"its":[111],"into":[113],"solo-like":[115],"one":[116],"based":[117],"on":[118],"pre-trained":[120],"transformation.":[121],"Our":[122],"experiments":[123],"show":[124],"that":[125],"such":[126],"improves":[132],"SID":[134],"accuracy":[135],"noticeably.":[136]},"counts_by_year":[{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
