{"id":"https://openalex.org/W2175575774","doi":"https://doi.org/10.1109/taslp.2015.2496226","title":"Study of Senone-Based Deep Neural Network Approaches for Spoken Language Recognition","display_name":"Study of Senone-Based Deep Neural Network Approaches for Spoken Language Recognition","publication_year":2015,"publication_date":"2015-10-30","ids":{"openalex":"https://openalex.org/W2175575774","doi":"https://doi.org/10.1109/taslp.2015.2496226","mag":"2175575774"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2015.2496226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2496226","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":["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/A5056267912","display_name":"Luciana Ferrer","orcid":"https://orcid.org/0000-0002-0426-8683"},"institutions":[{"id":"https://openalex.org/I151201029","display_name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","ror":"https://ror.org/03cqe8w59","country_code":"AR","type":"government","lineage":["https://openalex.org/I151201029","https://openalex.org/I4210123736","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I24354313","display_name":"Universidad de Buenos Aires","ror":"https://ror.org/0081fs513","country_code":"AR","type":"education","lineage":["https://openalex.org/I24354313"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Luciana Ferrer","raw_affiliation_strings":["CONICET, Argentina","Computer Science Department, Universidad de Buenos Aires, Argentina"],"raw_orcid":"https://orcid.org/0000-0002-0426-8683","affiliations":[{"raw_affiliation_string":"CONICET, Argentina","institution_ids":["https://openalex.org/I151201029"]},{"raw_affiliation_string":"Computer Science Department, Universidad de Buenos Aires, Argentina","institution_ids":["https://openalex.org/I24354313"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101648572","display_name":"Yun Lei","orcid":"https://orcid.org/0000-0003-4572-6078"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Lei","raw_affiliation_strings":["Facebook, Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook, Inc., USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mitchell McLaren","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, California, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103585404","display_name":"Nicolas Scheffer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicolas Scheffer","raw_affiliation_strings":["Facebook, Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook, Inc., USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.394,"has_fulltext":false,"cited_by_count":81,"citation_normalized_percentile":{"value":0.99070311,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"24","issue":"1","first_page":"105","last_page":"116"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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":0.8314056396484375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7872196435928345},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6136474609375},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5945878028869629},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.591659665107727},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4799004793167114},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46851038932800293},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.45697200298309326},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45065709948539734},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.44913968443870544},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4367935359477997},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4367557764053345},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42536792159080505},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4237675070762634},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36418288946151733}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8314056396484375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7872196435928345},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6136474609375},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5945878028869629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.591659665107727},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4799004793167114},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46851038932800293},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.45697200298309326},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45065709948539734},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.44913968443870544},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4367935359477997},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4367557764053345},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42536792159080505},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4237675070762634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36418288946151733},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2015.2496226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2496226","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G5172121936","display_name":null,"funder_award_id":"D10PC20024","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W61053364","https://openalex.org/W70590613","https://openalex.org/W156922528","https://openalex.org/W167195097","https://openalex.org/W1490504384","https://openalex.org/W1491108479","https://openalex.org/W1512214071","https://openalex.org/W1538131130","https://openalex.org/W1969121061","https://openalex.org/W1994935303","https://openalex.org/W2005708641","https://openalex.org/W2031585553","https://openalex.org/W2038262612","https://openalex.org/W2039057510","https://openalex.org/W2056119007","https://openalex.org/W2076954782","https://openalex.org/W2098196171","https://openalex.org/W2113832997","https://openalex.org/W2114719288","https://openalex.org/W2136879537","https://openalex.org/W2139622435","https://openalex.org/W2147768505","https://openalex.org/W2150769028","https://openalex.org/W2153181479","https://openalex.org/W2158069733","https://openalex.org/W2160815625","https://openalex.org/W2183016404","https://openalex.org/W2183984815","https://openalex.org/W2185814970","https://openalex.org/W2295880672","https://openalex.org/W2340176088","https://openalex.org/W2396197757","https://openalex.org/W2396983800","https://openalex.org/W2399270979","https://openalex.org/W2400962240","https://openalex.org/W2402698866","https://openalex.org/W2405584646","https://openalex.org/W2408021097","https://openalex.org/W2887979278","https://openalex.org/W3198419098","https://openalex.org/W6697225806","https://openalex.org/W6712105053","https://openalex.org/W6712689738","https://openalex.org/W6713198051","https://openalex.org/W6713204639","https://openalex.org/W6713741301","https://openalex.org/W6753916174"],"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/W2539884462"],"abstract_inverted_index":{"This":[0],"paper":[1],"compares":[2],"different":[3,36,69,239],"approaches":[4,25,56,129,158],"for":[5,16,167,200],"using":[6,163],"deep":[7],"neural":[8],"networks":[9],"(DNNs)":[10],"trained":[11,180,202],"to":[12,30,45,49,60,71,110,119,160,185,218,233],"predict":[13,72,120],"senone":[14],"posteriors":[15],"the":[17,58,73,92,96,100,103,112,117,121,133,144,190,241,249],"task":[18,247],"of":[19,54,75,154,156],"spoken":[20],"language":[21,77,244,252],"recognition":[22,245],"(SLR).":[23],"These":[24],"have":[26,40],"recently":[27],"been":[28,43],"found":[29],"outperform":[31,143],"various":[32],"baseline":[33],"systems":[34,176],"on":[35,136,227,236],"datasets,":[37],"but":[38],"they":[39],"not":[41],"yet":[42],"compared":[44],"each":[46,76],"other":[47,145],"or":[48,94],"a":[50,79,88,164,219],"common":[51],"baseline.":[52],"Two":[53],"these":[55,127,157],"use":[57,111,178],"DNNs":[59,179,201],"generate":[61],"feature":[62],"vectors":[63],"which":[64],"are":[65,84],"then":[66],"processed":[67],"in":[68,91,187],"ways":[70],"score":[74],"given":[78],"test":[80,169,228],"sample.":[81],"The":[82],"features":[83,138],"extracted":[85],"either":[86],"from":[87,95,230],"bottleneck":[89,137],"layer":[90],"DNN":[93,118],"output":[97],"layer.":[98],"In":[99],"third":[101],"approach,":[102],"standard":[104],"i-vector":[105,141,225],"extraction":[106],"procedure":[107,199],"is":[108],"modified":[109],"senones":[113],"as":[114],"classes":[115],"and":[116,130,194,215,248],"zeroth":[122],"order":[123],"statistics.":[124],"We":[125,148],"compare":[126],"three":[128],"conclude":[131],"that":[132,151,174,177],"approach":[134,166],"based":[135],"followed":[139],"by":[140],"modeling":[142],"two":[146,237],"approaches.":[147],"also":[149],"show":[150,211],"score-level":[152],"fusion":[153],"some":[155],"leads":[159,184],"gains":[161],"over":[162,189],"single":[165,192],"short-duration":[168],"samples.":[170],"Finally,":[171],"we":[172,195,210],"demonstrate":[173],"fusing":[175],"with":[181,203,205],"several":[182],"languages":[183,204],"improvements":[186,212],"performance":[188],"best":[191],"system,":[193],"propose":[196],"an":[197],"adaptation":[198],"less":[206],"available":[207],"data.":[208],"Overall,":[209],"between":[213],"40%":[214],"70%":[216],"relative":[217],"state-of-the-art":[220],"Gaussian":[221],"mixture":[222],"model":[223],"(GMM)":[224],"system":[226],"durations":[229],"3":[231],"seconds":[232,235],"120":[234],"significantly":[238],"tasks:":[240],"NIST":[242],"2009":[243],"evaluation":[246],"DARPA":[250],"RATS":[251],"identification":[253],"task.":[254]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}