{"id":"https://openalex.org/W2996319710","doi":"https://doi.org/10.1145/3368926.3369700","title":"Deep Learning Approach for Singer Voice Classification of Vietnamese Popular Music","display_name":"Deep Learning Approach for Singer Voice Classification of Vietnamese Popular Music","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2996319710","doi":"https://doi.org/10.1145/3368926.3369700","mag":"2996319710"},"language":"en","primary_location":{"id":"doi:10.1145/3368926.3369700","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368926.3369700","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth International Symposium on Information and Communication Technology  - SoICT 2019","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.12111","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045407393","display_name":"To\u00e0n Ph\u1ea1m V\u0103n","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Toan Pham Van","raw_affiliation_strings":["R&D Lab, Sun Inc, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"R&D Lab, Sun Inc, Hanoi, Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083505237","display_name":"Ngoc Tran","orcid":"https://orcid.org/0000-0003-0479-9561"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ngoc Tran Ngo Quang","raw_affiliation_strings":["R&D Lab, Sun Inc, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"R&D Lab, Sun Inc, Hanoi, Vietnam","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040778937","display_name":"T\u1ea1 Minh Thanh","orcid":null},"institutions":[{"id":"https://openalex.org/I131359167","display_name":"Le Quy Don Technical University","ror":"https://ror.org/04wgyjv21","country_code":"VN","type":"education","lineage":["https://openalex.org/I131359167"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Ta Minh Thanh","raw_affiliation_strings":["Le Quy Don Technical University, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"Le Quy Don Technical University, Hanoi, Vietnam","institution_ids":["https://openalex.org/I131359167"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045407393"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.334,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.58471276,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"255","last_page":"260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.9991999864578247,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9914000034332275,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.787126898765564},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7346322536468506},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.586835503578186},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5714912414550781},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5433417558670044},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5263934135437012},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.514845073223114},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4734480082988739},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.47257936000823975},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.4687861204147339},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.4354468882083893},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4169095456600189},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4135770797729492},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38723722100257874},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3856057822704315},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.1936054229736328},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.14420002698898315}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.787126898765564},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7346322536468506},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.586835503578186},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5714912414550781},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5433417558670044},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5263934135437012},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.514845073223114},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4734480082988739},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.47257936000823975},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.4687861204147339},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.4354468882083893},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4169095456600189},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4135770797729492},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38723722100257874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3856057822704315},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.1936054229736328},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.14420002698898315},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3368926.3369700","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368926.3369700","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth International Symposium on Information and Communication Technology  - SoICT 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.12111","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.12111","pdf_url":"https://arxiv.org/pdf/2102.12111","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.12111","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.12111","pdf_url":"https://arxiv.org/pdf/2102.12111","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6700000166893005,"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":28,"referenced_works":["https://openalex.org/W49012378","https://openalex.org/W99956014","https://openalex.org/W102958777","https://openalex.org/W130906308","https://openalex.org/W163807827","https://openalex.org/W1510532633","https://openalex.org/W1901129140","https://openalex.org/W2047484428","https://openalex.org/W2062227835","https://openalex.org/W2089204011","https://openalex.org/W2111331420","https://openalex.org/W2142384583","https://openalex.org/W2145487065","https://openalex.org/W2169327228","https://openalex.org/W2557283755","https://openalex.org/W2573926402","https://openalex.org/W2618530766","https://openalex.org/W2669032454","https://openalex.org/W2761434131","https://openalex.org/W2774707525","https://openalex.org/W2888839658","https://openalex.org/W2902420888","https://openalex.org/W2907919236","https://openalex.org/W2916985722","https://openalex.org/W2922094867","https://openalex.org/W2950635152","https://openalex.org/W2964070952","https://openalex.org/W2964307722"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2160511961","https://openalex.org/W2112047474"],"abstract_inverted_index":{"Singer":[0],"voice":[1,64,80],"classification":[2],"is":[3,21,75],"a":[4,12,19,39,89,94,122],"meaningful":[5],"task":[6],"in":[7],"the":[8,44,56,67,78,82,114,142,150],"digital":[9],"era.":[10],"With":[11],"huge":[13],"number":[14],"of":[15,50,58,72,116,124,136],"songs":[16,127],"today,":[17],"identifying":[18],"singer":[20,90],"very":[22],"helpful":[23],"for":[24],"music":[25,28],"information":[26],"retrieval,":[27],"properties":[29],"indexing,":[30],"and":[31,62],"so":[32],"on.":[33],"In":[34,85],"this":[35],"paper,":[36],"we":[37,92,119],"propose":[38,93],"new":[40],"method":[41],"to":[42,76,87,146],"identify":[43],"singer's":[45,79],"name":[46],"based":[47],"on":[48,121,149],"analysis":[49],"Vietnamese":[51,126],"popular":[52],"music.":[53],"We":[54,132],"employ":[55],"use":[57],"vocal":[59],"segment":[60],"detection":[61],"singing":[63],"separation":[65],"as":[66,105],"preprocessing":[68],"steps.":[69],"The":[70],"purpose":[71],"these":[73],"steps":[74],"extract":[77],"from":[81,109,128],"mixture":[83],"sound.":[84],"order":[86],"build":[88],"classifier,":[91],"neural":[95],"network":[96],"architecture":[97],"working":[98],"with":[99,138],"Mel":[100],"Frequency":[101],"Cepstral":[102],"Coefficient":[103],"(MFCC)":[104],"extracted":[106],"input":[107],"features":[108],"said":[110],"vocal.":[111],"To":[112],"verify":[113],"accuracy":[115,135],"our":[117],"methods,":[118],"evaluate":[120],"dataset":[123],"300":[125],"18":[129],"famous":[130],"singers.":[131],"achieve":[133],"an":[134],"92.84%":[137],"5-fold":[139],"stratified":[140],"cross-validation,":[141],"best":[143],"result":[144],"compared":[145],"other":[147],"methods":[148],"same":[151],"data":[152],"set.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2019-12-26T00:00:00"}
