{"id":"https://openalex.org/W2801768581","doi":"https://doi.org/10.1109/icassp.2018.8462403","title":"DNN Based Embeddings for Language Recognition","display_name":"DNN Based Embeddings for Language Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2801768581","doi":"https://doi.org/10.1109/icassp.2018.8462403","mag":"2801768581"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/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":true,"raw_author_name":"Alicia Lozano-Diez","raw_affiliation_strings":["Audias-UAM, Universidad Autonoma de Madrid, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Audias-UAM, Universidad Autonoma de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I63634437"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064238041","display_name":"Old\u0159ich Plchot","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oldrich Plchot","raw_affiliation_strings":["BUT, Speech@FIT, Czech Republic"],"affiliations":[{"raw_affiliation_string":"BUT, Speech@FIT, Czech Republic","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076315361","display_name":"Pavel Mat\u011bjka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pavel Matejka","raw_affiliation_strings":["BUT, Speech@FIT, Czech Republic"],"affiliations":[{"raw_affiliation_string":"BUT, Speech@FIT, Czech Republic","institution_ids":[]}]},{"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":["Audias-UAM, Universidad Autonoma de Madrid, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Audias-UAM, Universidad Autonoma de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I63634437"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063156730"],"corresponding_institution_ids":["https://openalex.org/I63634437"],"apc_list":null,"apc_paid":null,"fwci":2.9319,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92835837,"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":"5184","last_page":"5188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9988999962806702,"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":0.992900013923645,"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":0.7838887572288513},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4276980459690094},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4047698378562927},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3950117826461792}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7838887572288513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4276980459690094},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4047698378562927},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3950117826461792}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W98857008","https://openalex.org/W128628490","https://openalex.org/W162588823","https://openalex.org/W2046056978","https://openalex.org/W2078169166","https://openalex.org/W2098196171","https://openalex.org/W2114925438","https://openalex.org/W2121812409","https://openalex.org/W2136879537","https://openalex.org/W2150769028","https://openalex.org/W2160815625","https://openalex.org/W2185814970","https://openalex.org/W2259317772","https://openalex.org/W2280397712","https://openalex.org/W2295880672","https://openalex.org/W2340176088","https://openalex.org/W2405950182","https://openalex.org/W2406215990","https://openalex.org/W2406392101","https://openalex.org/W2408021097","https://openalex.org/W2484582464","https://openalex.org/W2491474862","https://openalex.org/W2515572005","https://openalex.org/W2518048674","https://openalex.org/W2518633166","https://openalex.org/W2742430148","https://openalex.org/W2748488820","https://openalex.org/W2749006664","https://openalex.org/W6603929392","https://openalex.org/W6605273041","https://openalex.org/W6606560281","https://openalex.org/W6662018943","https://openalex.org/W6677390740","https://openalex.org/W6677847058","https://openalex.org/W6686687092","https://openalex.org/W6687442591","https://openalex.org/W6695378040","https://openalex.org/W6697225806"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0,13,46,66],"this":[1,96],"work,":[2],"we":[3,52,68,99,111,139,169],"present":[4],"a":[5,19,54,70,113],"language":[6],"identification":[7],"(LID)":[8],"system":[9],"based":[10,72],"on":[11,73,134],"embeddings.":[12,109],"our":[14,132],"case,":[15],"an":[16],"embedding":[17],"is":[18,34],"fixed-length":[20],"vector":[21],"(similar":[22],"to":[23,36,41,48,63,108,126,162],"i-vector)":[24],"that":[25],"represents":[26],"the":[27,42,119,141,175],"whole":[28,120],"utterance,":[29],"but":[30],"unlike":[31],"i-vector":[32],"it":[33],"designed":[35],"contain":[37],"mostly":[38],"information":[39],"relevant":[40],"target":[43],"task":[44],"(LID).":[45],"order":[47],"obtain":[49],"these":[50],"embeddings,":[51],"train":[53,118],"deep":[55],"neural":[56,80],"network":[57,81,121],"(DNN)":[58],"with":[59,122],"sequence":[60],"summarization":[61],"layer":[62,116],"classify":[64],"languages.":[65,129],"particular,":[67],"trained":[69],"DNN":[71],"bidirectional":[74],"long":[75],"short-term":[76],"memory":[77],"(BLSTM)":[78],"recurrent":[79],"(RNN)":[82],"layers,":[83],"whose":[84,105],"frame-by-frame":[85],"outputs":[86,106],"are":[87],"summarized":[88],"into":[89],"mean":[90],"and":[91,117,138,145,164],"standard":[92],"deviation":[93],"statistics.":[94],"After":[95],"pooling":[97],"layer,":[98],"add":[100,112],"two":[101],"fully":[102],"connected":[103],"layers":[104],"correspond":[107],"Finally,":[110],"softmax":[114],"output":[115],"multi-class":[123],"cross-entropy":[124],"objective":[125],"discriminate":[127],"between":[128],"We":[130],"report":[131],"results":[133],"NIST":[135],"LRE":[136],"2015":[137],"compare":[140],"performance":[142,161],"of":[143],"embeddings":[144,157],"corresponding":[146],"i-vectors":[147,163],"both":[148],"modeled":[149],"by":[150,165],"Gaussian":[151],"Linear":[152],"Classifier":[153],"(GLC).":[154],"Using":[155],"only":[156],"resulted":[158],"in":[159],"comparable":[160],"performing":[166],"score-level":[167],"fusion":[168],"achieved":[170],"7.3%":[171],"relative":[172],"improvement":[173],"over":[174],"baseline.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}