{"id":"https://openalex.org/W4292968575","doi":"https://doi.org/10.1109/jstsp.2022.3201445","title":"Efficient Self-Supervised Learning Representations for Spoken Language Identification","display_name":"Efficient Self-Supervised Learning Representations for Spoken Language Identification","publication_year":2022,"publication_date":"2022-08-24","ids":{"openalex":"https://openalex.org/W4292968575","doi":"https://doi.org/10.1109/jstsp.2022.3201445"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2022.3201445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3201445","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-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/A5091096053","display_name":"Hexin Liu","orcid":"https://orcid.org/0000-0002-3998-9229"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hexin Liu","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-3998-9229","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059858850","display_name":"Leibny Paola Garcia","orcid":"https://orcid.org/0000-0002-7449-5726"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leibny Paola Garcia Perera","raw_affiliation_strings":["CLSP and HLT-COE, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-7449-5726","affiliations":[{"raw_affiliation_string":"CLSP and HLT-COE, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010202250","display_name":"Andy W. H. Khong","orcid":"https://orcid.org/0000-0002-0708-4791"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Andy W. H. Khong","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-0708-4791","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072241540","display_name":"Suzy J Styles","orcid":"https://orcid.org/0000-0003-3517-9680"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Suzy J. Styles","raw_affiliation_strings":["Psychology, School of Social Sciences, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Psychology, School of Social Sciences, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["CLSP and HLT-COE, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0001-5976-0897","affiliations":[{"raw_affiliation_string":"CLSP and HLT-COE, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.608,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.93709676,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"16","issue":"6","first_page":"1296","last_page":"1307"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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":0.9958999752998352,"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":0.806252121925354},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.5696684122085571},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5374854803085327},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5373185276985168},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5229959487915039},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5196593999862671},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4920641779899597},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.47979527711868286},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.44307276606559753},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42462003231048584},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3839162290096283},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35139042139053345},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09497171640396118}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.806252121925354},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5696684122085571},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5374854803085327},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5373185276985168},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5229959487915039},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5196593999862671},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4920641779899597},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.47979527711868286},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.44307276606559753},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42462003231048584},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3839162290096283},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35139042139053345},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09497171640396118},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2022.3201445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3201445","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G3921862303","display_name":null,"funder_award_id":"JHU IO 90071537","funder_id":"https://openalex.org/F4320320766","funder_display_name":"Nanyang Technological University"},{"id":"https://openalex.org/G5877145623","display_name":"CCRI: ENS: Next Generation Tools for Spoken Language Science & Technology","funder_award_id":"2120435","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1983072039","https://openalex.org/W2104457544","https://openalex.org/W2166637769","https://openalex.org/W2172287020","https://openalex.org/W2185814970","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2408021097","https://openalex.org/W2752782242","https://openalex.org/W2794506738","https://openalex.org/W2807627734","https://openalex.org/W2888924726","https://openalex.org/W2890964092","https://openalex.org/W2902094805","https://openalex.org/W2963032538","https://openalex.org/W2963163009","https://openalex.org/W2972433488","https://openalex.org/W2973049979","https://openalex.org/W2979826702","https://openalex.org/W3008434450","https://openalex.org/W3010814938","https://openalex.org/W3024869864","https://openalex.org/W3095410713","https://openalex.org/W3163361649","https://openalex.org/W3180180466","https://openalex.org/W3197380209","https://openalex.org/W3197580070","https://openalex.org/W3198275944","https://openalex.org/W3198429080","https://openalex.org/W3198614662","https://openalex.org/W3207041304","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4283069819","https://openalex.org/W6603931906","https://openalex.org/W6606123296","https://openalex.org/W6631362777","https://openalex.org/W6638667902","https://openalex.org/W6696449567","https://openalex.org/W6739901393","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6780226713","https://openalex.org/W6795952400","https://openalex.org/W6802946626"],"related_works":["https://openalex.org/W2158491338","https://openalex.org/W2807901368","https://openalex.org/W2133733652","https://openalex.org/W2072658171","https://openalex.org/W2606392311","https://openalex.org/W2320042380","https://openalex.org/W4385956668","https://openalex.org/W2595172197","https://openalex.org/W2900895161","https://openalex.org/W4293305277"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"has":[2],"been":[3],"widely":[4],"exploited":[5],"to":[6,35,89,97,101,243],"learn":[7],"powerful":[8],"speech":[9,203],"representations.":[10],"The":[11,110],"premise":[12],"of":[13,64,72,105,180,239,250],"this":[14,77],"paper":[15],"is":[16,112,124],"that":[17,130],"these":[18,140],"learned":[19],"self-supervised":[20],"representations":[21,38,107],"contain":[22],"irrelevant":[23,103,132],"information":[24,42,104,133],"for":[25,43,118],"a":[26,48,236],"particular":[27],"downstream":[28],"task.":[29],"Hence,":[30],"we":[31,60],"investigate":[32],"efficient":[33],"methods":[34,142],"compute":[36],"reliable":[37],"and":[39,121,147,153,187,190,199,226,253],"discard":[40],"redundant":[41],"language":[44],"identification":[45],"(LID)":[46],"using":[47],"pre-trained":[49],"multilingual":[50],"wav2vec":[51,65,168],"2.0":[52,169],"model.":[53,246],"To":[54],"determine":[55],"an":[56],"optimal":[57],"basic":[58],"system,":[59],"compare":[61],"the":[62,73,79,86,106,113,122,125,144,154,163,171,181,205,215,232,244,255,260,265,269],"performance":[63],"features":[66,166,267],"extracted":[67],"from":[68],"different":[69],"inner":[70],"layers":[71],"context":[74],"network.":[75],"For":[76],"approach,":[78],"x-vector":[80],"self-attention":[81],"LID":[82],"(XSA-LID)":[83],"model":[84,146,173,218,258,262],"forms":[85],"backbone":[87],"used":[88],"discriminate":[90],"between":[91],"distinct":[92],"languages.":[93],"We":[94,138],"then":[95],"propose":[96],"employ":[98],"two":[99,141],"mechanisms":[100],"reduce":[102],"in":[108,143,157,178,204,208,248],"LID.":[109],"first":[111],"attentive":[114],"squeeze-and-excitation":[115],"(SE)":[116],"block":[117,129],"dimension-wise":[119],"scaling":[120],"second":[123],"linear":[126],"bottleneck":[127],"(LBN)":[128],"reduces":[131],"by":[134],"nonlinear":[135],"dimension":[136],"reduction.":[137],"incorporate":[139],"XSA-LID":[145,172,245,261],"conduct":[148],"experiments":[149],"on":[150,184,194,223,231,268],"AP19-OLR":[151,185,224,270],"data":[152,156,207,225,234],"MLS14":[155,206,233],"NIST":[158,209],"LRE":[159,210],"2017.":[160],"By":[161],"replacing":[162],"previous":[164],"input":[165],"with":[167,235],"features,":[170],"achieves":[174,219],"63.79%":[175],"relative":[176,192,221],"improvement":[177,193,222,230],"terms":[179,249],"average":[182,251],"cost":[183,252],"data,":[186],"40.42%,":[188],"41.54%":[189],"18.97%":[191],"3":[195],"s,":[196],"10":[197],"s":[198,201],"30":[200],"test":[202],"2017,":[211],"respectively.":[212],"In":[213],"addition,":[214],"proposed":[216,256],"LBN-XSA":[217,257],"9.85%":[220],"over":[227],"10%":[228],"overall":[229],"modest":[237],"number":[238],"additional":[240],"parameters":[241],"compared":[242],"Finally,":[247],"accuracy,":[254],"outperforms":[259],"which":[263],"adopts":[264],"fine-tuned":[266],"data.":[271]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}