{"id":"https://openalex.org/W2939634425","doi":"https://doi.org/10.1109/icassp.2019.8682749","title":"Boundary Discriminative Large Margin Cosine Loss for Text-independent Speaker Verification","display_name":"Boundary Discriminative Large Margin Cosine Loss for Text-independent Speaker Verification","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939634425","doi":"https://doi.org/10.1109/icassp.2019.8682749","mag":"2939634425"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5053549702","display_name":"Rongjin Li","orcid":"https://orcid.org/0000-0002-0178-5167"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rongjin Li","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368048","display_name":"Na Li","orcid":"https://orcid.org/0000-0001-9545-3050"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Li","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043757154","display_name":"Deyi Tuo","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deyi Tuo","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770786","display_name":"Meng Yu","orcid":"https://orcid.org/0000-0003-2554-2888"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Yu","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5053549702"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":3.2204,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.93618298,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6321","last_page":"6325"},"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":0.9998999834060669,"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":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8865180015563965},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7265062928199768},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7231523394584656},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6322557926177979},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5584791302680969},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5053494572639465},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5036336779594421},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4928560256958008},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4300110638141632},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.42120468616485596},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16068485379219055},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15065303444862366}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8865180015563965},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7265062928199768},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7231523394584656},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6322557926177979},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5584791302680969},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5053494572639465},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5036336779594421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4928560256958008},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4300110638141632},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.42120468616485596},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16068485379219055},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15065303444862366},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2046056978","https://openalex.org/W2121812409","https://openalex.org/W2150769028","https://openalex.org/W2183341477","https://openalex.org/W2219249508","https://openalex.org/W2402146185","https://openalex.org/W2406312423","https://openalex.org/W2584329820","https://openalex.org/W2612434969","https://openalex.org/W2696967604","https://openalex.org/W2746742816","https://openalex.org/W2748488820","https://openalex.org/W2802973008","https://openalex.org/W2888897023","https://openalex.org/W2888968865","https://openalex.org/W2890964092","https://openalex.org/W2962898354","https://openalex.org/W2963466847","https://openalex.org/W2963576203","https://openalex.org/W2963899139","https://openalex.org/W6662018943","https://openalex.org/W6688816777","https://openalex.org/W6712930963","https://openalex.org/W6713727690","https://openalex.org/W6737575990","https://openalex.org/W6748257384","https://openalex.org/W6754496211"],"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/W3148366653"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"network":[2,19,92],"based":[3],"speaker":[4,12,67,86],"embeddings":[5],"have":[6],"attracted":[7],"much":[8],"attention":[9],"in":[10,46,65],"text-independent":[11],"verification":[13],"task.":[14],"In":[15],"addition":[16],"to":[17,59,100,127],"the":[18,25,31,38,61,66,78,82,85,91,101],"architecture,":[20],"an":[21,51],"appropriate":[22],"design":[23],"of":[24,40],"loss":[26,132],"function":[27],"is":[28],"crucial":[29],"for":[30,77],"deep":[32],"discriminative":[33,56,62],"embedding":[34],"extractor.":[35],"Inspired":[36],"by":[37],"success":[39],"Large":[41],"Margin":[42],"Cosine":[43],"Loss":[44],"(LMCL)":[45],"face":[47],"recognition,":[48],"we":[49],"propose":[50],"enhanced":[52],"LMCL":[53,57,128],"named":[54],"boundary":[55],"(BD-LMCL)":[58],"emphasize":[60],"information":[63],"inherited":[64],"boundaries.":[68],"Unlike":[69],"LMCL,":[70],"where":[71],"all":[72],"training":[73,93],"samples":[74,83,98],"contribute":[75],"equally":[76],"objective":[79],"function,":[80],"only":[81],"around":[84],"boundaries":[87,102],"are":[88,103],"considered":[89],"during":[90],"with":[94],"BD-LMCL.":[95],"Specifically,":[96],"those":[97],"close":[99],"dynamically":[104],"selected":[105],"using":[106],"top-k":[107],"zero-one":[108],"loss.":[109],"Experimental":[110],"results":[111],"on":[112],"a":[113],"short":[114],"duration":[115],"corpus":[116],"Android":[117],"Cellphone":[118],"and":[119,129],"NIST":[120],"SRE":[121],"2012":[122],"demonstrate":[123],"better":[124],"performance":[125],"compared":[126],"other":[130],"popular":[131],"functions.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}