{"id":"https://openalex.org/W2518048674","doi":"https://doi.org/10.21437/interspeech.2016-1584","title":"Exploiting Hidden-Layer Responses of Deep Neural Networks for Language Recognition","display_name":"Exploiting Hidden-Layer Responses of Deep Neural Networks for Language Recognition","publication_year":2016,"publication_date":"2016-08-28","ids":{"openalex":"https://openalex.org/W2518048674","doi":"https://doi.org/10.21437/interspeech.2016-1584","mag":"2518048674"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-1584","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-1584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100760516","display_name":"Ruizhi Li","orcid":"https://orcid.org/0000-0002-2496-5224"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruizhi Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047596805","display_name":"Sri Harish Mallidi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sri Harish Mallidi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luk\u00e1\u0161 Burget","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064238041","display_name":"Old\u0159ich Plchot","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Old\u0159ich Plchot","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3265","last_page":"3269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9977999925613403,"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":0.9957000017166138,"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":0.7818268537521362},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7080661058425903},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6348257064819336},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6227093935012817},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5939761400222778},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5868597626686096},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5688675045967102},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48613378405570984},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.48577144742012024},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4561213552951813},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4499170482158661},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4315013885498047},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.42249345779418945},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.213718980550766}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7818268537521362},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7080661058425903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6348257064819336},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6227093935012817},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5939761400222778},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5868597626686096},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5688675045967102},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48613378405570984},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.48577144742012024},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4561213552951813},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4499170482158661},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4315013885498047},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.42249345779418945},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.213718980550766},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2016-1584","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-1584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W1506806321","https://openalex.org/W2153181479"],"related_works":["https://openalex.org/W2395910192","https://openalex.org/W2113687551","https://openalex.org/W2112752961","https://openalex.org/W2124808007","https://openalex.org/W2387081965","https://openalex.org/W1998541766","https://openalex.org/W2064542902","https://openalex.org/W1886560176","https://openalex.org/W2262900283","https://openalex.org/W1985349217"],"abstract_inverted_index":{"Abstract":[0],":":[1],"The":[2,63,114,128,155],"most":[3,134],"popular":[4],"way":[5],"to":[6,165],"apply":[7],"Deep":[8],"Neural":[9],"Network":[10],"(DNN)":[11],"for":[12,73,77,137],"Language":[13],"IDentification":[14],"(LID)":[15],"involves":[16],"the":[17,54,71,75,87,100,133,142,159,166],"extraction":[18],"of":[19,52,116],"bottleneck":[20],"features":[21,34,136],"from":[22,58],"a":[23,38,43,59,78,123],"network":[24],"that":[25],"was":[26,48],"trained":[27,143],"on":[28,69,141],"automatic":[29],"speech":[30,80],"recognition":[31,139,153],"task.":[32],"These":[33],"are":[35,162],"modeled":[36],"using":[37,122],"classical":[39,167],"I-vector":[40,168],"system.":[41],"Recently,":[42],"more":[44],"direct":[45,88],"DNN":[46,89],"approach":[47,90,148,161],"proposed,":[49],"it":[50],"consists":[51],"estimating":[53],"language":[55,138,152],"posteriors":[56],"directly":[57],"stacked":[60],"frames":[61,76],"input.":[62],"final":[64],"decision":[65],"score":[66],"is":[67,107,119],"based":[68,140],"averaging":[70,99],"scores":[72],"all":[74,93,111],"given":[79],"segment.":[81],"In":[82],"this":[83,117,147],"paper,":[84],"we":[85],"extended":[86],"by":[91,109,158],"modeling":[92],"hidden-layer":[94,112],"activations":[95],"rather":[96],"than":[97],"just":[98],"output":[101],"scores.":[102],"One":[103],"super-vector":[104],"per":[105],"utterance":[106],"formed":[108],"concatenating":[110],"responses.":[113],"dimensionality":[115],"vector":[118,131],"then":[120],"reduced":[121],"Principal":[124],"Component":[125],"Analysis":[126],"(PCA).":[127],"obtained":[129],"reduce":[130],"summarizes":[132],"discriminative":[135],"DNNs.":[144],"We":[145],"evaluated":[146],"in":[149],"NIST":[150],"2015":[151],"evaluation.":[154],"performances":[156],"achieved":[157],"proposed":[160],"very":[163],"competitive":[164],"baseline.":[169]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}