{"id":"https://openalex.org/W2717402182","doi":"https://doi.org/10.1109/icassp.2017.7953183","title":"Discriminative autoencoders for speaker verification","display_name":"Discriminative autoencoders for speaker verification","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2717402182","doi":"https://doi.org/10.1109/icassp.2017.7953183","mag":"2717402182"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5048338308","display_name":"Hung-Shin Lee","orcid":"https://orcid.org/0000-0001-7044-9434"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Shin Lee","raw_affiliation_strings":["Academia Sinica, Institute of Information Science, Taiwan","Department of Electrical Engineering, National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Institute of Information Science, Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Department of Electrical Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062616905","display_name":"Yu-Ding Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Ding Lu","raw_affiliation_strings":["Academia Sinica, Research Center for Information Technology Innovation, Taiwan","[Research Center for Information Technology Innovation, Academia Sinica, Taiwan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Research Center for Information Technology Innovation, Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"[Research Center for Information Technology Innovation, Academia Sinica, Taiwan]","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028115568","display_name":"Chin-Cheng Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chin-Cheng Hsu","raw_affiliation_strings":["Academia Sinica, Institute of Information Science, Taiwan","Institute of Information Science Academia Sinica Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Institute of Information Science, Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Institute of Information Science Academia Sinica Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Academia Sinica, Research Center for Information Technology Innovation, Taiwan","[Research Center for Information Technology Innovation, Academia Sinica, Taiwan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Research Center for Information Technology Innovation, Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"[Research Center for Information Technology Innovation, Academia Sinica, Taiwan]","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Academia Sinica, Institute of Information Science, Taiwan","Institute of Information Science Academia Sinica Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Institute of Information Science, Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Institute of Information Science Academia Sinica Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028285867","display_name":"Shyh\u2010Kang Jeng","orcid":"https://orcid.org/0000-0001-8960-9995"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shyh-Kang Jeng","raw_affiliation_strings":["Department of Electrical Engineering, National Taiwan University, Taiwan","[Dept. of Electrical Engineering, National Taiwan University, Taiwan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[Dept. of Electrical Engineering, National Taiwan University, Taiwan]","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6611,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.88445515,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"12","issue":null,"first_page":"5375","last_page":"5379"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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":0.9937000274658203,"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/discriminative-model","display_name":"Discriminative model","score":0.7663756012916565},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.749784529209137},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6773720979690552},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6597738862037659},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6540428400039673},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6338096261024475},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6127573847770691},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.5878444314002991},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5634515881538391},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5173463225364685},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5102100372314453},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.499906063079834},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4970267117023468},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.49325960874557495},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48320138454437256},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39015674591064453},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.29558444023132324}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7663756012916565},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.749784529209137},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6773720979690552},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6597738862037659},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6540428400039673},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6338096261024475},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6127573847770691},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5878444314002991},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5634515881538391},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5173463225364685},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5102100372314453},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.499906063079834},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4970267117023468},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.49325960874557495},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48320138454437256},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39015674591064453},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29558444023132324},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W204572845","https://openalex.org/W1533861849","https://openalex.org/W1544785557","https://openalex.org/W1583048384","https://openalex.org/W1601124178","https://openalex.org/W1770825568","https://openalex.org/W1965968825","https://openalex.org/W2039057510","https://openalex.org/W2046056978","https://openalex.org/W2049244943","https://openalex.org/W2053159670","https://openalex.org/W2078169166","https://openalex.org/W2110439892","https://openalex.org/W2114925438","https://openalex.org/W2122825543","https://openalex.org/W2135346934","https://openalex.org/W2145094598","https://openalex.org/W2146502635","https://openalex.org/W2148091317","https://openalex.org/W2150769028","https://openalex.org/W2159786793","https://openalex.org/W2166469867","https://openalex.org/W2183016404","https://openalex.org/W2187089797","https://openalex.org/W2395750323","https://openalex.org/W2397634864","https://openalex.org/W2399100775","https://openalex.org/W2402919203","https://openalex.org/W2403686171","https://openalex.org/W2406312423","https://openalex.org/W2407127962","https://openalex.org/W2919115771","https://openalex.org/W2997574889","https://openalex.org/W4231109964","https://openalex.org/W4234330420","https://openalex.org/W6608411242","https://openalex.org/W6631943919","https://openalex.org/W6681096077","https://openalex.org/W6681435938","https://openalex.org/W6681739674","https://openalex.org/W6686491854","https://openalex.org/W6712325649","https://openalex.org/W6713521420","https://openalex.org/W6713633562","https://openalex.org/W6713727690"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,50],"learning":[4],"and":[5,59],"scoring":[6],"framework":[7,16],"based":[8],"on":[9,144],"neural":[10],"networks":[11],"for":[12,34],"speaker":[13,35,83,92],"verification.":[14],"The":[15,37],"employs":[17],"an":[18],"autoencoder":[19],"as":[20,108],"its":[21],"primary":[22],"structure":[23,48],"while":[24],"three":[25],"factors":[26],"are":[27,84,102],"jointly":[28],"considered":[29],"in":[30,66,90,152],"the":[31,42,47,63,67,71,81,91,96,111,116,139,145,149,153,162,168],"objective":[32],"function":[33],"discrimination.":[36],"first":[38],"one,":[39],"relating":[40],"to":[41,55,75,104,109],"sample":[43],"reconstruction":[44],"error,":[45],"makes":[46],"essentially":[49],"generative":[51],"model,":[52],"which":[53],"benefits":[54],"learn":[56],"most":[57],"salient":[58],"useful":[60],"properties":[61],"of":[62,98,113,119,129,141,148,164],"data.":[64],"Functioning":[65],"middlemost":[68],"hidden":[69],"layer,":[70],"other":[72],"two":[73],"attempt":[74],"ensure":[76],"that":[77],"utterances":[78,135],"spoken":[79],"by":[80,126,137],"same":[82],"mapped":[85],"into":[86],"similar":[87],"identity":[88,100,131],"codes":[89,101],"discriminative":[93],"subspace,":[94],"where":[95],"dispersion":[97],"all":[99],"maximized":[103],"some":[105],"extent":[106],"so":[107],"avoid":[110],"effect":[112],"over-concentration.":[114],"Finally,":[115],"decision":[117],"score":[118],"each":[120],"utterance":[121],"pair":[122],"is":[123],"simply":[124],"computed":[125],"cosine":[127],"similarity":[128],"their":[130],"codes.":[132],"Dealing":[133],"with":[134],"represented":[136],"i-vectors,":[138],"results":[140],"experiments":[142],"conducted":[143],"male":[146],"portion":[147],"core":[150],"task":[151],"NIST":[154],"2010":[155],"Speaker":[156],"Recognition":[157],"Evaluation":[158],"(SRE)":[159],"significantly":[160],"demonstrate":[161],"merits":[163],"our":[165],"approach":[166],"over":[167],"conventional":[169],"PLDA":[170],"method.":[171]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}