{"id":"https://openalex.org/W2806993054","doi":"https://doi.org/10.1109/iscslp.2018.8706570","title":"Angular Softmax Loss for End-to-end Speaker Verification","display_name":"Angular Softmax Loss for End-to-end Speaker Verification","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2806993054","doi":"https://doi.org/10.1109/iscslp.2018.8706570","mag":"2806993054"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1806.03464","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085236897","display_name":"Yutian Li","orcid":"https://orcid.org/0000-0003-1810-3000"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutian Li","raw_affiliation_strings":["Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China","[Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"[Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China]","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046668357","display_name":"Feng Gao","orcid":"https://orcid.org/0000-0002-1825-328X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Gao","raw_affiliation_strings":["Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China","[Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"[Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China]","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010173604","display_name":"Zhijian Ou","orcid":"https://orcid.org/0000-0002-9018-5074"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijian Ou","raw_affiliation_strings":["Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China","[Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"[Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China]","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100298903","display_name":"Jiasong Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiasong Sun","raw_affiliation_strings":["Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China","[Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"[Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China]","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.8425,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79970911,"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":"190","last_page":"194"},"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":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.990586519241333},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8172421455383301},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7694847583770752},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6906911134719849},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5984576940536499},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5191777944564819},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5162336826324463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4580378532409668},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4264729917049408},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3324170708656311},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3000819683074951}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.990586519241333},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8172421455383301},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7694847583770752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6906911134719849},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5984576940536499},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5191777944564819},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5162336826324463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4580378532409668},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4264729917049408},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3324170708656311},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3000819683074951},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iscslp.2018.8706570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1806.03464","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.03464","pdf_url":"https://arxiv.org/pdf/1806.03464","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.1806.03464","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1806.03464","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1806.03464","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.03464","pdf_url":"https://arxiv.org/pdf/1806.03464","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2806993054.pdf","grobid_xml":"https://content.openalex.org/works/W2806993054.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1762484328","https://openalex.org/W2096733369","https://openalex.org/W2114925438","https://openalex.org/W2121812409","https://openalex.org/W2150769028","https://openalex.org/W2560919222","https://openalex.org/W2587150483","https://openalex.org/W2609296554","https://openalex.org/W2612434969","https://openalex.org/W2747238065","https://openalex.org/W2748488820","https://openalex.org/W2766049740","https://openalex.org/W2766191375","https://openalex.org/W2949117887","https://openalex.org/W2962832278","https://openalex.org/W2963702081","https://openalex.org/W3099206234","https://openalex.org/W6631362777","https://openalex.org/W6637956674","https://openalex.org/W6638667902","https://openalex.org/W6682889407","https://openalex.org/W6732884072","https://openalex.org/W6733275487","https://openalex.org/W6736780073","https://openalex.org/W6737575990","https://openalex.org/W6738450829","https://openalex.org/W6745415975","https://openalex.org/W6745983287"],"related_works":["https://openalex.org/W2743258233","https://openalex.org/W2883935556","https://openalex.org/W2970216048","https://openalex.org/W2782592381","https://openalex.org/W2891409152","https://openalex.org/W2103897043","https://openalex.org/W2020437063","https://openalex.org/W2972986505","https://openalex.org/W2806993054","https://openalex.org/W2963902346"],"abstract_inverted_index":{"End-to-end":[0],"speaker":[1,24,43,76,123],"verification":[2,124],"systems":[3,156],"have":[4],"received":[5],"increasing":[6],"interests.":[7],"The":[8],"traditional":[9],"i-vector":[10],"approach":[11,30],"trains":[12,32],"a":[13,17,33,37,45],"generative":[14],"model":[15,35],"(basically":[16],"factor-analysis":[18],"model)":[19],"to":[20,40],"extract":[21],"i-vectors":[22],"as":[23,67],"embeddings.":[25],"In":[26,52],"contrast,":[27],"the":[28,49,68,100,134,141,147,152,177],"end-to-end":[29,75,122,155],"directly":[31],"discriminative":[34,42,90],"(often":[36],"neural":[38],"network)":[39],"learn":[41,88],"embeddings;":[44],"crucial":[46],"component":[47],"is":[48,61,103],"training":[50,140],"criterion.":[51],"this":[53,114],"paper,":[54],"we":[55],"use":[56],"angular":[57],"softmax":[58,84,93],"(A-softmax),":[59],"which":[60],"originally":[62],"proposed":[63],"for":[64,71,107],"face":[65],"verification,":[66],"loss":[69,94,120],"function":[70],"feature":[72],"learning":[73],"in":[74,113,139,146,162],"verification.":[77],"By":[78],"introducing":[79],"margins":[80],"between":[81],"classes":[82],"into":[83,121],"loss,":[85,97],"A-softmax":[86,119,138],"can":[87],"more":[89],"features":[91],"than":[92],"and":[95,98,105,125,143,165,175],"triplet":[96],"at":[99],"same":[101],"time,":[102],"easy":[104],"stable":[106],"usage.":[108],"We":[109,117,131],"make":[110],"two":[111],"contributions":[112],"work.":[115],"1)":[116],"introduce":[118],"achieve":[126],"significant":[127],"EER":[128],"reductions.":[129],"2)":[130],"find":[132],"that":[133],"combination":[135],"of":[136,154,172,179],"using":[137,144,180],"front-end":[142],"PLDA":[145],"back-end":[148],"scoring":[149],"further":[150],"boosts":[151],"performance":[153],"under":[157],"short":[158],"utterance":[159],"condition":[160],"(short":[161],"both":[163],"enrollment":[164],"test).":[166],"Experiments":[167],"are":[168],"conducted":[169],"on":[170],"part":[171],"Fisher":[173],"dataset":[174],"demonstrate":[176],"improvements":[178],"A-softmax.":[181]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}