{"id":"https://openalex.org/W2997714987","doi":"https://doi.org/10.1109/icis46139.2019.8940235","title":"End-to-End Convolutional Neural Network for Speaker Recognition Based on Joint Supervision","display_name":"End-to-End Convolutional Neural Network for Speaker Recognition Based on Joint Supervision","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2997714987","doi":"https://doi.org/10.1109/icis46139.2019.8940235","mag":"2997714987"},"language":"en","primary_location":{"id":"doi:10.1109/icis46139.2019.8940235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icis46139.2019.8940235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACIS 18th International Conference on Computer and Information Science (ICIS)","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/A5078695545","display_name":"Wanglei Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]},{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wanglei Shi","raw_affiliation_strings":["Key Laboratory of Convergent Media and Intelligent Technology, Ministry of Education Communication University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Convergent Media and Intelligent Technology, Ministry of Education Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I1327237609","https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062793914","display_name":"Feng Shuang","orcid":"https://orcid.org/0000-0002-4733-4732"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Shuang","raw_affiliation_strings":["Key Laboratory of Convergent Media and Intelligent Technology, Ministry of Education Communication University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Convergent Media and Intelligent Technology, Ministry of Education Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I1327237609","https://openalex.org/I75689368"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5078695545"],"corresponding_institution_ids":["https://openalex.org/I1327237609","https://openalex.org/I75689368"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59430323,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"385","last_page":"389"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9976000189781189,"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":0.9962999820709229,"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":0.8363620042800903},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.768539547920227},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7007414102554321},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6888843178749084},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.657121479511261},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5715232491493225},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5527099370956421},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5489514470100403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.548832893371582},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.5296242833137512},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5274239778518677},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4839649498462677},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.46602651476860046},{"id":"https://openalex.org/keywords/neocognitron","display_name":"Neocognitron","score":0.4643922448158264}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363620042800903},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.768539547920227},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7007414102554321},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6888843178749084},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.657121479511261},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5715232491493225},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5527099370956421},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5489514470100403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.548832893371582},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.5296242833137512},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5274239778518677},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4839649498462677},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.46602651476860046},{"id":"https://openalex.org/C121144440","wikidata":"https://www.wikidata.org/wiki/Q669754","display_name":"Neocognitron","level":4,"score":0.4643922448158264},{"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/icis46139.2019.8940235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icis46139.2019.8940235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACIS 18th International Conference on Computer and Information Science (ICIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1965359654","https://openalex.org/W1990942610","https://openalex.org/W1993482042","https://openalex.org/W2026358225","https://openalex.org/W2039057510","https://openalex.org/W2046015436","https://openalex.org/W2046056978","https://openalex.org/W2054060258","https://openalex.org/W2078169166","https://openalex.org/W2123768812","https://openalex.org/W2129244720","https://openalex.org/W2147147599","https://openalex.org/W2166111255","https://openalex.org/W2793150943","https://openalex.org/W2890964092","https://openalex.org/W2949117887","https://openalex.org/W2964351684"],"related_works":["https://openalex.org/W4282920028","https://openalex.org/W2166713742","https://openalex.org/W3215620389","https://openalex.org/W2261468771","https://openalex.org/W3092663764","https://openalex.org/W2371791833","https://openalex.org/W2069265260","https://openalex.org/W2389191077","https://openalex.org/W4385719553","https://openalex.org/W3081952170"],"abstract_inverted_index":{"Speech":[0],"recognition":[1,23,36,41,80,141,161],"accuracy":[2,81],"has":[3],"been":[4,27,31],"greatly":[5,32],"improved":[6,33,163],"due":[7],"to":[8,83,112,119],"the":[9,39,50,57,61,65,73,79,100,114,140,151,168,172],"application":[10],"of":[11,20,52,60,72,102,107,116,139,156],"Deep":[12],"Neural":[13,90],"Network":[14,91],"(DNN)":[15],"in":[16,64],"it.":[17],"A":[18],"variety":[19],"DNN-based":[21],"speaker":[22,40,96,160],"methods":[24],"have":[25,30],"recently":[26],"proposed,":[28],"which":[29,98],"over":[34],"traditional":[35,66],"methods.":[37],"However,":[38],"model":[42,74,103,142],"based":[43,125],"on":[44,126],"DNN":[45],"is":[46,75,93,110,134,143,162,174],"usually":[47],"used":[48,94,111],"for":[49,95,159],"extraction":[51,58],"bottleneck":[53],"features":[54],"or":[55],"as":[56],"part":[59],"sufficient":[62],"statistics":[63],"i-vector":[67],"model.":[68],"The":[69,105,137,146],"training":[70],"speed":[71],"not":[76],"ideal,":[77],"and":[78,122,129,171],"needs":[82],"be":[84],"improved.":[85,145],"In":[86],"this":[87],"paper,":[88],"Convolutional":[89],"(CNN)":[92],"recognition,":[97],"reduces":[99],"complexity":[101],"training.":[104],"method":[106,124],"hopping":[108],"connection":[109],"solve":[113],"problem":[115],"network":[117],"degradation":[118],"some":[120],"extent,":[121],"a":[123],"softmax":[127],"loss":[128,131],"center":[130],"joint":[132],"supervision":[133],"also":[135],"introduced.":[136],"performance":[138,173],"further":[144],"experimental":[147],"results":[148],"show":[149],"that":[150],"Equal":[152],"Error":[153],"Rate":[154],"(EER)":[155],"End-to-End":[157],"CNN":[158],"by":[164],"13.4%":[165],"compared":[166],"with":[167],"baseline":[169],"method,":[170],"better.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}