{"id":"https://openalex.org/W4375868770","doi":"https://doi.org/10.1109/icassp49357.2023.10095116","title":"Exploring Universal Singing Speech Language Identification Using Self-Supervised Learning Based Front-End Features","display_name":"Exploring Universal Singing Speech Language Identification Using Self-Supervised Learning Based Front-End Features","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868770","doi":"https://doi.org/10.1109/icassp49357.2023.10095116"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095116","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101694303","display_name":"Xingming Wang","orcid":"https://orcid.org/0009-0004-1301-7597"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xingming Wang","raw_affiliation_strings":["Duke Kunshan University,Data Science Research Center,Kunshan,China","Data Science Research Center, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Data Science Research Center,Kunshan,China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101693338","display_name":"Hao Wu","orcid":"https://orcid.org/0000-0002-1035-6567"},"institutions":[{"id":"https://openalex.org/I1323199999","display_name":"Central Intelligence Agency","ror":"https://ror.org/0135c5n64","country_code":"US","type":"government","lineage":["https://openalex.org/I1323199999"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Wu","raw_affiliation_strings":["ByteDance,Speech, Audio, and Music Intelligence (SAMI) Group,China","Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, China"],"affiliations":[{"raw_affiliation_string":"ByteDance,Speech, Audio, and Music Intelligence (SAMI) Group,China","institution_ids":["https://openalex.org/I1323199999"]},{"raw_affiliation_string":"Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014869234","display_name":"Chen Ding","orcid":"https://orcid.org/0000-0002-9001-8575"},"institutions":[{"id":"https://openalex.org/I1323199999","display_name":"Central Intelligence Agency","ror":"https://ror.org/0135c5n64","country_code":"US","type":"government","lineage":["https://openalex.org/I1323199999"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Ding","raw_affiliation_strings":["ByteDance,Speech, Audio, and Music Intelligence (SAMI) Group,China","Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, China"],"affiliations":[{"raw_affiliation_string":"ByteDance,Speech, Audio, and Music Intelligence (SAMI) Group,China","institution_ids":["https://openalex.org/I1323199999"]},{"raw_affiliation_string":"Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018343941","display_name":"Chuanzeng Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I1323199999","display_name":"Central Intelligence Agency","ror":"https://ror.org/0135c5n64","country_code":"US","type":"government","lineage":["https://openalex.org/I1323199999"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuanzeng Huang","raw_affiliation_strings":["ByteDance,Speech, Audio, and Music Intelligence (SAMI) Group,China","Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, China"],"affiliations":[{"raw_affiliation_string":"ByteDance,Speech, Audio, and Music Intelligence (SAMI) Group,China","institution_ids":["https://openalex.org/I1323199999"]},{"raw_affiliation_string":"Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351449","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-6406-1983"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Duke Kunshan University,Data Science Research Center,Kunshan,China","Data Science Research Center, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Data Science Research Center,Kunshan,China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101694303"],"corresponding_institution_ids":["https://openalex.org/I4210159968"],"apc_list":null,"apc_paid":null,"fwci":0.4066,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54215435,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"33","issue":null,"first_page":"1","last_page":"5"},"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":0.9909999966621399,"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":0.9901000261306763,"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":0.8851878643035889},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.7509428262710571},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7505009174346924},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6216996908187866},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6097901463508606},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5959151387214661},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.526274561882019},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.511293888092041},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.500899076461792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4696967601776123},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4281526207923889},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.23779883980751038},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14794570207595825},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.06681427359580994},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.062048524618148804}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8851878643035889},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7509428262710571},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7505009174346924},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6216996908187866},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6097901463508606},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5959151387214661},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.526274561882019},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.511293888092041},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.500899076461792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4696967601776123},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4281526207923889},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.23779883980751038},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14794570207595825},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.06681427359580994},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.062048524618148804},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095116","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336618","display_name":"Science and Technology Program of Suzhou","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2594633041","https://openalex.org/W2726515241","https://openalex.org/W2752782242","https://openalex.org/W2794506738","https://openalex.org/W2903006902","https://openalex.org/W2963626623","https://openalex.org/W2995181338","https://openalex.org/W3024869864","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3045349544","https://openalex.org/W3119308075","https://openalex.org/W3122349645","https://openalex.org/W3139878283","https://openalex.org/W3162588046","https://openalex.org/W3180180466","https://openalex.org/W3198275944","https://openalex.org/W3198694222","https://openalex.org/W3200345197","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4225096077","https://openalex.org/W4226502599","https://openalex.org/W4394647634","https://openalex.org/W6734194636","https://openalex.org/W6740167877","https://openalex.org/W6771467084","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2366077683","https://openalex.org/W1501596003","https://openalex.org/W2368036937"],"abstract_inverted_index":{"Despite":[0],"the":[1,19,42,55,70,83,87,98],"great":[2],"performance":[3,84],"of":[4,12,21,86],"language":[5,23,37,65,79,91],"identification":[6,24,66],"(LID),":[7],"there":[8],"is":[9],"a":[10,29],"lack":[11],"large-scale":[13],"singing":[14,22,36,63,89],"LID":[15],"databases":[16],"to":[17],"support":[18],"research":[20],"(SLID).":[25],"This":[26],"paper":[27],"proposed":[28],"over":[30],"3200":[31],"hours":[32],"dataset":[33],"used":[34],"for":[35,58,106],"identification,":[38],"called":[39],"Slingua.":[40],"As":[41],"baseline,":[43],"we":[44,81],"explore":[45],"two":[46],"self-supervised":[47],"learning":[48],"(SSL)":[49],"models,":[50],"WavLM":[51],"and":[52,61,108],"Wav2vec2,":[53],"as":[54],"feature":[56],"extractors":[57],"both":[59],"SLID":[60],"universal":[62,88],"speech":[64,78,90],"(ULID),":[67],"compared":[68],"with":[69,77],"traditional":[71],"handcraft":[72],"feature.":[73],"Moreover,":[74],"by":[75],"training":[76],"corpus,":[80],"compare":[82],"difference":[85],"identification.":[92],"The":[93,111],"final":[94],"results":[95],"show":[96],"that":[97],"SSL-based":[99],"features":[100],"exhibit":[101],"more":[102],"robust":[103],"generalization,":[104],"especially":[105],"low-resource":[107],"open-set":[109],"scenarios.":[110],"database":[112],"can":[113],"be":[114],"downloaded":[115],"following":[116],"this":[117],"repository:":[118],"https://github.com/Doctor-Do/Slingua.":[119]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}
