{"id":"https://openalex.org/W2890704021","doi":"https://doi.org/10.1109/slt.2018.8639622","title":"Frame-Level Speaker Embeddings for Text-Independent Speaker Recognition and Analysis of End-to-End Model","display_name":"Frame-Level Speaker Embeddings for Text-Independent Speaker Recognition and Analysis of End-to-End Model","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2890704021","doi":"https://doi.org/10.1109/slt.2018.8639622","mag":"2890704021"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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/A5020263683","display_name":"Suwon Shon","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suwon Shon","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100662187","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-2445-2605"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Tang","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":87,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1007","last_page":"1013"},"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":0.9950000047683716,"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":0.9947999715805054,"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":0.7775066494941711},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7087643146514893},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6878896951675415},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6279870867729187},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5495908260345459},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5424779653549194},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5371900796890259},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5160691142082214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43577584624290466},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4149169325828552},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.2604188323020935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7775066494941711},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7087643146514893},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6878896951675415},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6279870867729187},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5495908260345459},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5424779653549194},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5371900796890259},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5160691142082214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43577584624290466},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4149169325828552},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2604188323020935},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2018.8639622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.699999988079071,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2039057510","https://openalex.org/W2072349636","https://openalex.org/W2078169166","https://openalex.org/W2090958120","https://openalex.org/W2150769028","https://openalex.org/W2167136086","https://openalex.org/W2485419308","https://openalex.org/W2515741950","https://openalex.org/W2726515241","https://openalex.org/W2741480356","https://openalex.org/W2748318213","https://openalex.org/W2748488820","https://openalex.org/W2750822272","https://openalex.org/W2752168051","https://openalex.org/W2802488037","https://openalex.org/W2890964092","https://openalex.org/W2919115771","https://openalex.org/W2962679215","https://openalex.org/W2962776659","https://openalex.org/W2962778323","https://openalex.org/W2962813140","https://openalex.org/W2962922562","https://openalex.org/W4234330420","https://openalex.org/W6722197923","https://openalex.org/W6726295259","https://openalex.org/W6742911084","https://openalex.org/W6743489131","https://openalex.org/W6743680795","https://openalex.org/W6765774462"],"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":{"In":[0,100],"this":[1],"paper,":[2],"we":[3,43],"propose":[4],"a":[5],"Convolutional":[6],"Neural":[7],"Network":[8],"(CNN)":[9],"based":[10],"speaker":[11,17,36,50,145],"recognition":[12,37],"model":[13,38],"for":[14,117,140],"extracting":[15],"robust":[16],"embeddings.":[18],"The":[19,121],"embedding":[20,30],"can":[21],"be":[22],"extracted":[23],"efficiently":[24],"with":[25,40],"linear":[26],"activation":[27],"in":[28],"the":[29,35,45,60,64,74,88,107,118,130,133,138],"layer.":[31,55],"To":[32],"understand":[33],"how":[34],"operates":[39],"text-independent":[41],"input,":[42],"modify":[44],"structure":[46],"to":[47,63,72,77,106,128,143],"extract":[48],"frame-level":[49,102],"embeddings":[51,103],"from":[52,59],"each":[53],"hidden":[54],"We":[56,85],"feed":[57],"utterances":[58],"TIMIT":[61],"dataset":[62],"trained":[65],"network":[66],"and":[67,81,136],"use":[68],"several":[69],"proxy":[70],"tasks":[71],"study":[73],"networks":[75,89,131],"ability":[76],"represent":[78],"speech":[79],"input":[80],"differentiate":[82],"voice":[83],"identity.":[84],"found":[86],"that":[87,104],"are":[90,111],"better":[91],"at":[92,132],"discriminating":[93],"broad":[94],"phonetic":[95,109],"classes":[96,110],"than":[97],"individual":[98],"phonemes.":[99],"particular,":[101],"belong":[105],"same":[108,119],"similar":[112],"(based":[113],"on":[114],"cosine":[115],"distance)":[116],"speaker.":[120],"frame":[122,134],"level":[123],"representation":[124],"also":[125],"allows":[126],"us":[127],"analyze":[129],"level,":[135],"has":[137],"potential":[139],"other":[141],"analyses":[142],"improve":[144],"recognition.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}