{"id":"https://openalex.org/W2408175559","doi":"https://doi.org/10.21437/interspeech.2015-164","title":"An end-to-end approach to language identification in short utterances using convolutional neural networks","display_name":"An end-to-end approach to language identification in short utterances using convolutional neural networks","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2408175559","doi":"https://doi.org/10.21437/interspeech.2015-164","mag":"2408175559"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-164","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10486/674566","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063156730","display_name":"Alicia Lozano-D\u00edez","orcid":"https://orcid.org/0000-0002-5918-8568"},"institutions":[{"id":"https://openalex.org/I63634437","display_name":"Universidad Aut\u00f3noma de Madrid","ror":"https://ror.org/01cby8j38","country_code":"ES","type":"education","lineage":["https://openalex.org/I63634437"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alicia Lozano-Diez","raw_affiliation_strings":["ATVS-Biometric Recognition Group, Universidad Autonoma de Madrid, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"ATVS-Biometric Recognition Group, Universidad Autonoma de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I63634437"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097646021","display_name":"Ruben Zazo-Candil","orcid":null},"institutions":[{"id":"https://openalex.org/I63634437","display_name":"Universidad Aut\u00f3noma de Madrid","ror":"https://ror.org/01cby8j38","country_code":"ES","type":"education","lineage":["https://openalex.org/I63634437"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Ruben Zazo-Candil","raw_affiliation_strings":["ATVS-Biometric Recognition Group, Universidad Autonoma de Madrid, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"ATVS-Biometric Recognition Group, Universidad Autonoma de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I63634437"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089369295","display_name":"Javier G\u00f3nzalez-Dom\u00ednguez","orcid":null},"institutions":[{"id":"https://openalex.org/I63634437","display_name":"Universidad Aut\u00f3noma de Madrid","ror":"https://ror.org/01cby8j38","country_code":"ES","type":"education","lineage":["https://openalex.org/I63634437"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Gonzalez-Dominguez","raw_affiliation_strings":["ATVS-Biometric Recognition Group, Universidad Autonoma de Madrid, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"ATVS-Biometric Recognition Group, Universidad Autonoma de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I63634437"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089438058","display_name":"Doroteo T. Toledano","orcid":"https://orcid.org/0000-0003-1159-6455"},"institutions":[{"id":"https://openalex.org/I63634437","display_name":"Universidad Aut\u00f3noma de Madrid","ror":"https://ror.org/01cby8j38","country_code":"ES","type":"education","lineage":["https://openalex.org/I63634437"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Doroteo T. Toledano","raw_affiliation_strings":["ATVS-Biometric Recognition Group, Universidad Autonoma de Madrid, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"ATVS-Biometric Recognition Group, Universidad Autonoma de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I63634437"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011964320","display_name":"Joaqu\u00edn Gonz\u00e1lez-Rodr\u00edguez","orcid":"https://orcid.org/0000-0003-0910-2575"},"institutions":[{"id":"https://openalex.org/I63634437","display_name":"Universidad Aut\u00f3noma de Madrid","ror":"https://ror.org/01cby8j38","country_code":"ES","type":"education","lineage":["https://openalex.org/I63634437"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Joaquin Gonzalez-Rodriguez","raw_affiliation_strings":["ATVS-Biometric Recognition Group, Universidad Autonoma de Madrid, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"ATVS-Biometric Recognition Group, Universidad Autonoma de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I63634437"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5097646021"],"corresponding_institution_ids":["https://openalex.org/I63634437"],"apc_list":null,"apc_paid":null,"fwci":9.347,"has_fulltext":true,"cited_by_count":55,"citation_normalized_percentile":{"value":0.97908163,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"403","last_page":"407"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9986000061035156,"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":0.9975000023841858,"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/nist","display_name":"NIST","score":0.8094373941421509},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8008590936660767},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7291347980499268},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.655083954334259},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6225061416625977},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.59201580286026},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5880791544914246},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5718950033187866},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.5284380912780762},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.526667058467865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5131148099899292},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4555354118347168},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43567782640457153},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2786668539047241},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07346215844154358}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8094373941421509},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8008590936660767},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7291347980499268},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.655083954334259},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6225061416625977},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.59201580286026},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5880791544914246},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5718950033187866},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.5284380912780762},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.526667058467865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5131148099899292},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4555354118347168},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43567782640457153},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2786668539047241},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07346215844154358},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2015-164","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:repositorio.uam.es:10486/674566","is_oa":true,"landing_page_url":"http://hdl.handle.net/10486/674566","pdf_url":"http://hdl.handle.net/10486/674566","source":{"id":"https://openalex.org/S4306400963","display_name":"Biblos-e Archivo (Universidad Aut\u00f3noma de Madrid)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63634437","host_organization_name":"Universidad Aut\u00f3noma de Madrid","host_organization_lineage":["https://openalex.org/I63634437"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:repositorio.uam.es:10486/674566","is_oa":true,"landing_page_url":"http://hdl.handle.net/10486/674566","pdf_url":"http://hdl.handle.net/10486/674566","source":{"id":"https://openalex.org/S4306400963","display_name":"Biblos-e Archivo (Universidad Aut\u00f3noma de Madrid)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63634437","host_organization_name":"Universidad Aut\u00f3noma de Madrid","host_organization_lineage":["https://openalex.org/I63634437"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8110045202","display_name":null,"funder_award_id":"CMC-V2","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"}],"funders":[{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2408175559.pdf"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W58434446","https://openalex.org/W167195097","https://openalex.org/W1524333225","https://openalex.org/W1982774639","https://openalex.org/W1983072039","https://openalex.org/W1995562189","https://openalex.org/W2056119007","https://openalex.org/W2072128103","https://openalex.org/W2146194791","https://openalex.org/W2150769028","https://openalex.org/W2183984815","https://openalex.org/W2310919327","https://openalex.org/W2405476549","https://openalex.org/W2406392101","https://openalex.org/W2408021097","https://openalex.org/W4231109964","https://openalex.org/W4387560871"],"related_works":["https://openalex.org/W2160451571","https://openalex.org/W2916997151","https://openalex.org/W2495256954","https://openalex.org/W2259317772","https://openalex.org/W2949174760","https://openalex.org/W1998541766","https://openalex.org/W2064542902","https://openalex.org/W2262900283","https://openalex.org/W1985349217","https://openalex.org/W2098508228"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,119],"propose":[4],"an":[5],"end-to-end":[6],"approach":[7],"to":[8,44,86,98,110,143],"the":[9,29,66,78,106,125],"language":[10],"identification":[11],"(LID)":[12],"problem":[13],"based":[14],"on":[15],"Convolutional":[16],"Deep":[17],"Neural":[18],"Networks":[19],"(CDNNs).":[20],"The":[21,91],"use":[22],"of":[23,50,52,62,73,80,89,108,145,150],"CDNNs":[24],"is":[25],"mainly":[26],"motivated":[27],"by":[28],"ability":[30],"they":[31],"have":[32],"shown":[33],"when":[34],"modeling":[35],"speech":[36],"signals,":[37],"and":[38,124],"their":[39],"relatively":[40],"low-cost":[41],"with":[42,128],"respect":[43],"other":[45],"deep":[46],"architectures":[47],"in":[48,59,148],"terms":[49,149],"number":[51,107],"free":[53],"parameters.":[54],"We":[55],"evaluate":[56],"different":[57],"configurations":[58],"a":[60,129],"subset":[61],"8":[63],"languages":[64],"within":[65],"NIST":[67],"Language":[68],"Recognition":[69],"Evaluation":[70],"2009":[71],"Voice":[72],"America":[74],"(VOA)":[75],"dataset,":[76],"for":[77],"task":[79],"short":[81],"test":[82],"durations":[83],"(segments":[84],"up":[85],"3":[87],"seconds":[88],"speech).":[90],"proposed":[92],"CDNN-based":[93,122],"systems":[94,123],"achieve":[95],"comparable":[96],"performances":[97],"our":[99,138],"baseline":[100,127],"i-vector":[101,126],"system,":[102],"while":[103],"reducing":[104],"drastically":[105],"parameters":[109],"tune":[111],"(at":[112],"least":[113],"100":[114],"times":[115],"fewer":[116],"parameters).":[117],"Then,":[118],"combine":[120],"these":[121],"simple":[130],"fusion":[131],"at":[132],"score":[133],"level.":[134],"This":[135],"combination":[136],"outperforms":[137],"best":[139],"standalone":[140],"system":[141],"(up":[142],"11%":[144],"relative":[146],"improvement":[147],"EER).":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}