{"id":"https://openalex.org/W4288391343","doi":"https://doi.org/10.1109/taslp.2022.3190736","title":"A Discriminative Hierarchical PLDA-Based Model for Spoken Language Recognition","display_name":"A Discriminative Hierarchical PLDA-Based Model for Spoken Language Recognition","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4288391343","doi":"https://doi.org/10.1109/taslp.2022.3190736"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3190736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3190736","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2201.01364","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056267912","display_name":"Luciana Ferrer","orcid":"https://orcid.org/0000-0002-0426-8683"},"institutions":[{"id":"https://openalex.org/I4210144290","display_name":"Institute of Astronomy and Space Physics","ror":"https://ror.org/03rq94151","country_code":"AR","type":"facility","lineage":["https://openalex.org/I151201029","https://openalex.org/I24354313","https://openalex.org/I4210123736","https://openalex.org/I4210144290","https://openalex.org/I4387155568"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Luciana Ferrer","raw_affiliation_strings":["Instituto de Investigación en Ciencias de la Computación, CONICET-UBA, Buenos Aires, Argentina","n en Ciencias de la Computaci&#x00F3","Instituto de Investigaci&#x00F3"],"raw_orcid":"https://orcid.org/0000-0002-0426-8683","affiliations":[{"raw_affiliation_string":"Instituto de Investigación en Ciencias de la Computación, CONICET-UBA, Buenos Aires, Argentina","institution_ids":["https://openalex.org/I4210144290"]},{"raw_affiliation_string":"n en Ciencias de la Computaci&#x00F3","institution_ids":[]},{"raw_affiliation_string":"Instituto de Investigaci&#x00F3","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013886109","display_name":"Diego Cast\u00e1n","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Diego Castan","raw_affiliation_strings":["SRI International, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060382325","display_name":"Mitchell McLaren","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mitchell McLaren","raw_affiliation_strings":["SRI International, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103710557","display_name":"Aaron Lawson","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron Lawson","raw_affiliation_strings":["SRI International, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5802,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71378343,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"30","issue":null,"first_page":"2396","last_page":"2410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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":0.9984999895095825,"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":0.8520998954772949},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7817480564117432},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6115238070487976},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5517897605895996},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5378998517990112},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5102019309997559},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4846937954425812},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4803644120693207},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.43525487184524536},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.41363397240638733},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34887105226516724},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32955649495124817}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8520998954772949},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7817480564117432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6115238070487976},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5517897605895996},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5378998517990112},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5102019309997559},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4846937954425812},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4803644120693207},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.43525487184524536},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.41363397240638733},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34887105226516724},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32955649495124817},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2022.3190736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3190736","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2201.01364","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.01364","pdf_url":"https://arxiv.org/pdf/2201.01364","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"},{"id":"pmh:oai:ri.conicet.gov.ar:11336/204631","is_oa":true,"landing_page_url":"http://hdl.handle.net/11336/204631","pdf_url":null,"source":{"id":"https://openalex.org/S4306401400","display_name":"Conicet","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210104196","host_organization_name":"Centro Cient\u00edfico Tecnol\u00f3gico - Nordeste","host_organization_lineage":["https://openalex.org/I4210104196"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2201.01364","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.01364","pdf_url":"https://arxiv.org/pdf/2201.01364","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":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W123007118","https://openalex.org/W577640895","https://openalex.org/W1481604723","https://openalex.org/W1589137271","https://openalex.org/W1989124352","https://openalex.org/W1990942610","https://openalex.org/W2080297650","https://openalex.org/W2098196171","https://openalex.org/W2104457544","https://openalex.org/W2114719288","https://openalex.org/W2121812409","https://openalex.org/W2123768812","https://openalex.org/W2150769028","https://openalex.org/W2166637769","https://openalex.org/W2175575774","https://openalex.org/W2185814970","https://openalex.org/W2189305995","https://openalex.org/W2231567078","https://openalex.org/W2280397712","https://openalex.org/W2292087804","https://openalex.org/W2294814385","https://openalex.org/W2340176088","https://openalex.org/W2395619480","https://openalex.org/W2395750323","https://openalex.org/W2398046886","https://openalex.org/W2404617565","https://openalex.org/W2408548175","https://openalex.org/W2512856556","https://openalex.org/W2587150483","https://openalex.org/W2750167318","https://openalex.org/W2805504157","https://openalex.org/W2807627734","https://openalex.org/W2887979278","https://openalex.org/W2889466073","https://openalex.org/W2895654193","https://openalex.org/W2895676041","https://openalex.org/W2916297645","https://openalex.org/W2917756095","https://openalex.org/W2941349731","https://openalex.org/W2963032538","https://openalex.org/W2964010794","https://openalex.org/W2964351684","https://openalex.org/W2972712416","https://openalex.org/W2982474723","https://openalex.org/W3015304870","https://openalex.org/W3024098654","https://openalex.org/W3024541814","https://openalex.org/W3024880099","https://openalex.org/W3028785944","https://openalex.org/W3028954259","https://openalex.org/W3032479101","https://openalex.org/W3032558098","https://openalex.org/W3092791109","https://openalex.org/W3126634788","https://openalex.org/W3139878283","https://openalex.org/W3182396116","https://openalex.org/W3198290304","https://openalex.org/W4225098825","https://openalex.org/W4283014282","https://openalex.org/W4287100176","https://openalex.org/W4287641946","https://openalex.org/W4361745846","https://openalex.org/W6603931906","https://openalex.org/W6606123296","https://openalex.org/W6696449567","https://openalex.org/W6753916174","https://openalex.org/W6754205956","https://openalex.org/W6776605602","https://openalex.org/W6777664437","https://openalex.org/W6777781272","https://openalex.org/W6778672582","https://openalex.org/W6779192484","https://openalex.org/W6810350395"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W4311804456","https://openalex.org/W3103844505","https://openalex.org/W1987484445","https://openalex.org/W2113687551","https://openalex.org/W2112752961"],"abstract_inverted_index":{"Spoken":[0],"language":[1,13,177],"recognition":[2,63],"(SLR)":[3],"refers":[4],"to":[5,10,33,59,137,156,168,172,197,253],"the":[6,12,81,92,103,112,129,138,210,249],"automatic":[7],"process":[8],"used":[9],"determine":[11],"present":[14],"in":[15,24,53,219],"a":[16,31,54,87,107,116,145,165,183,199,230],"speech":[17,62],"sample.":[18],"SLR":[19,68,104],"is":[20,44,84,194],"an":[21,46,78],"important":[22],"task":[23,105],"its":[25],"own":[26],"right,":[27],"for":[28,49,57,95,159,213],"example,":[29,58],"as":[30,106,115,182],"tool":[32,48],"analyze":[34],"or":[35,64],"categorize":[36],"large":[37,133,223],"amounts":[38],"of":[39,73,128,161,185,189,215,232],"multi-lingual":[40],"data.":[41],"Further,":[42,142],"it":[43],"also":[45],"essential":[47],"selecting":[50],"downstream":[51],"applications":[52],"work":[55],"flow,":[56],"chose":[60],"appropriate":[61],"machine":[65],"translation":[66],"models.":[67],"systems":[69,228],"are":[70,153,180,251],"usually":[71],"composed":[72],"two":[74,150,187],"stages,":[75],"one":[76,89,155,167,212],"where":[77,149],"embedding":[79],"representing":[80],"audio":[82],"sample":[83],"extracted":[85],"and":[86,110,164,238,244],"second":[88,113,166],"which":[90],"computes":[91],"final":[93,176],"scores":[94,158,170,179],"each":[96,173],"language.":[97],"In":[98],"this":[99,205],"work,":[100],"we":[101,143],"approach":[102,148,207],"detection":[108,178,214],"problem":[109],"implement":[111],"stage":[114],"probabilistic":[117],"linear":[118],"discriminant":[119],"analysis":[120],"(PLDA)":[121],"model.":[122],"We":[123,202,225],"show":[124,203],"that":[125,204,248],"discriminative":[126],"training":[127],"PLDA":[130,151],"parameters":[131],"gives":[132],"gains":[134,250],"with":[135],"respect":[136],"usual":[139],"generative":[140],"training.":[141],"propose":[144],"novel":[146],"hierarchical":[147,206],"models":[152],"trained,":[154],"generate":[157,169],"clusters":[160],"highly-related":[162],"languages":[163],"conditional":[171],"cluster.":[174],"The":[175,191],"computed":[181],"combination":[184],"these":[186],"sets":[188],"scores.":[190],"complete":[192],"model":[193],"trained":[195],"discriminatively":[196],"optimize":[198],"cross-entropy":[200],"objective.":[201],"consistently":[208],"outperforms":[209],"non-hierarchical":[211],"highly":[216],"related":[217],"languages,":[218,237],"many":[220],"cases":[221],"by":[222],"margins.":[224],"train":[226],"our":[227],"on":[229,242],"collection":[231],"datasets":[233],"including":[234],"over":[235],"100":[236],"test":[239],"them":[240],"both":[241],"matched":[243],"mismatched":[245],"conditions,":[246],"showing":[247],"robust":[252],"condition":[254],"mismatch.":[255]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}