{"id":"https://openalex.org/W4392903482","doi":"https://doi.org/10.1109/icassp48485.2024.10446751","title":"Fine-Tuning Self-Supervised Models for Language Identification Using Orthonormal Constraint","display_name":"Fine-Tuning Self-Supervised Models for Language Identification Using Orthonormal Constraint","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903482","doi":"https://doi.org/10.1109/icassp48485.2024.10446751"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5076763342","display_name":"Amrutha Prasad","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH","CZ"],"is_corresponding":true,"raw_author_name":"Amrutha Prasad","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland","Idiap Research Institute, Martigny, Switzerland","Brno University of Technology, Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000784556","display_name":"Andr\u00e9s Carofilis","orcid":"https://orcid.org/0000-0001-9446-0152"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andr\u00e9s Carofilis","raw_affiliation_strings":["University of León,León,Spain"],"affiliations":[{"raw_affiliation_string":"University of León,León,Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028843673","display_name":"Geoffroy Vanderreydt","orcid":"https://orcid.org/0000-0001-7193-1863"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Geoffroy Vanderreydt","raw_affiliation_strings":["Ghent University - Imec,IDLab,Ghent,Belgium","IDLab, Ghent University - Imec, Ghent, Belgium"],"affiliations":[{"raw_affiliation_string":"Ghent University - Imec,IDLab,Ghent,Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"IDLab, Ghent University - Imec, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027738812","display_name":"Driss Khalil","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Driss Khalil","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland","Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084521938","display_name":"Srikanth Madikeri","orcid":"https://orcid.org/0000-0002-4361-784X"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Srikanth Madikeri","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland","Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076409146","display_name":"Petr Motl\u00ed\u010dek","orcid":"https://orcid.org/0000-0001-6467-1119"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH","CZ"],"is_corresponding":false,"raw_author_name":"Petr Motlicek","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland","Brno University of Technology, Brno, Czech Republic","Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052823509","display_name":"Christof Schuepbach","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christof Schuepbach","raw_affiliation_strings":["University of León,León,Spain"],"affiliations":[{"raw_affiliation_string":"University of León,León,Spain","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5076763342"],"corresponding_institution_ids":["https://openalex.org/I60587646","https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":1.3264,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82439815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"11921","last_page":"11925"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9927999973297119,"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/computer-science","display_name":"Computer science","score":0.7486833333969116},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7350202202796936},{"id":"https://openalex.org/keywords/orthonormal-basis","display_name":"Orthonormal basis","score":0.670712947845459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.630562961101532},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6115283370018005},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5990660190582275},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.5606177449226379},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5308939814567566},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5115379095077515},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3293658494949341}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7486833333969116},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7350202202796936},{"id":"https://openalex.org/C5806529","wikidata":"https://www.wikidata.org/wiki/Q2365325","display_name":"Orthonormal basis","level":2,"score":0.670712947845459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.630562961101532},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6115283370018005},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5990660190582275},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.5606177449226379},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5308939814567566},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5115379095077515},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3293658494949341},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:01JJ1GPXKPYHKYG5927Q37ESWT","is_oa":false,"landing_page_url":"http://hdl.handle.net/1854/LU-01JJ1GPXKPYHKYG5927Q37ESWT","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9798350344851","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1604974512","https://openalex.org/W2121812409","https://openalex.org/W2150769028","https://openalex.org/W2582930187","https://openalex.org/W2807627734","https://openalex.org/W2887499727","https://openalex.org/W2888867175","https://openalex.org/W2890964092","https://openalex.org/W2916297645","https://openalex.org/W2933138175","https://openalex.org/W3008912312","https://openalex.org/W3014528057","https://openalex.org/W3024869864","https://openalex.org/W3036601975","https://openalex.org/W3160641957","https://openalex.org/W3167533889","https://openalex.org/W3180180466","https://openalex.org/W3197798809","https://openalex.org/W3198275944","https://openalex.org/W3198429080","https://openalex.org/W3213029956","https://openalex.org/W4287645199","https://openalex.org/W4385245566","https://openalex.org/W4385822439","https://openalex.org/W6631362777","https://openalex.org/W6713762819","https://openalex.org/W6779919476","https://openalex.org/W6780218876","https://openalex.org/W6784162623","https://openalex.org/W6787335539","https://openalex.org/W6847363464"],"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/W2900895161","https://openalex.org/W4380838366","https://openalex.org/W2170073831"],"abstract_inverted_index":{"Self-supervised":[0],"models":[1,145],"trained":[2,147],"with":[3,98,148,169],"high":[4],"linguistic":[5],"diversity,":[6],"such":[7],"as":[8],"the":[9,17,89,111,125,134,159],"XLS-R":[10],"model,":[11],"can":[12,113],"be":[13,45,114],"effectively":[14],"fine-tuned":[15],"for":[16],"language":[18],"recognition":[19],"task.":[20],"Typically,":[21],"a":[22,39,128,132],"back-end":[23,36],"classifier":[24,130],"followed":[25],"by":[26,93],"statistics":[27],"pooling":[28],"layer":[29],"are":[30,146],"added":[31],"during":[32],"training.":[33],"Commonly":[34],"used":[35,139],"classifiers":[37,165],"require":[38],"large":[40],"number":[41,90],"of":[42,91,127],"parameters":[43,92],"to":[44,95,116],"trained,":[46],"which":[47],"is":[48,73,120],"not":[49],"ideal":[50],"in":[51,104,140,171],"limited":[52],"data":[53,151],"conditions.":[54],"In":[55],"this":[56],"work,":[57],"we":[58],"explore":[59],"smaller":[60],"parameter":[61],"back-ends":[62,168],"using":[63],"factorized":[64],"Time":[65],"Delay":[66],"Neural":[67],"Network":[68],"(TDNN-F).":[69],"The":[70,107,144],"TDNN-F":[71],"architecture":[72],"also":[74,123],"integrated":[75],"into":[76],"Emphasized":[77],"Channel":[78],"Attention,":[79],"Propagation":[80],"and":[81,101,131,152,158,175],"Aggregation-":[82],"TDNN":[83],"(ECAPA-TDNN)":[84],"models,":[85],"termed":[86],"ECAPA-TDNN-F,":[87],"reducing":[88],"30":[94],"50%":[96],"absolute,":[97],"competitive":[99],"accuracies":[100],"no":[102],"change":[103],"minimum":[105],"cost.":[106],"results":[108],"show":[109],"that":[110],"ECAPA-TDNN-F":[112],"extended":[115],"tasks":[117],"where":[118],"ECAPA-TDNN":[119],"suitable.":[121],"We":[122],"test":[124],"effectiveness":[126],"linear":[129,136,164],"variant,":[133],"Orthonormal":[135],"classifier,":[137],"previously":[138],"x-vector":[141],"type":[142],"systems.":[143],"NIST":[149,155],"LRE17":[150],"evaluated":[153],"on":[154],"LRE17,":[156],"LRE22":[157],"ATCO2":[160],"LID":[161],"datasets.":[162],"Both":[163],"outperform":[166],"conventional":[167],"improvements":[170],"accuracy":[172],"between":[173],"0.9%":[174],"9.1%.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}