{"id":"https://openalex.org/W2963181813","doi":"https://doi.org/10.1109/iscslp.2016.7918380","title":"Max-margin metric learning for speaker recognition","display_name":"Max-margin metric learning for speaker recognition","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2963181813","doi":"https://doi.org/10.1109/iscslp.2016.7918380","mag":"2963181813"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2016.7918380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5050701255","display_name":"Lantian Li","orcid":"https://orcid.org/0000-0003-4274-7930"},"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":"Lantian Li","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391494","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6992-7950"},"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":"Dong Wang","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023693837","display_name":"Xing Chao","orcid":"https://orcid.org/0000-0003-2574-4148"},"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":"Chao Xing","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084318285","display_name":"Thomas Fang Zheng","orcid":"https://orcid.org/0000-0002-0249-4767"},"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":"Thomas Fang Zheng","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, 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":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9965000152587891,"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/T10057","display_name":"Face and Expression Recognition","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/margin","display_name":"Margin (machine learning)","score":0.707850992679596},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6422975063323975},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6357662677764893},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6214663982391357},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4523778557777405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.450735479593277},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3542327880859375},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19744020700454712},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12833768129348755}],"concepts":[{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.707850992679596},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6422975063323975},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6357662677764893},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6214663982391357},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4523778557777405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.450735479593277},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3542327880859375},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19744020700454712},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12833768129348755},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2016.7918380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W17749540","https://openalex.org/W1589137271","https://openalex.org/W1916834241","https://openalex.org/W1958522516","https://openalex.org/W1990942610","https://openalex.org/W2070852568","https://openalex.org/W2077548500","https://openalex.org/W2107638917","https://openalex.org/W2112582577","https://openalex.org/W2118393783","https://openalex.org/W2123768812","https://openalex.org/W2130556178","https://openalex.org/W2150769028","https://openalex.org/W2152175008","https://openalex.org/W2186274992","https://openalex.org/W2395750323","https://openalex.org/W2406312423","https://openalex.org/W6600721324","https://openalex.org/W6675751002","https://openalex.org/W6677884823","https://openalex.org/W6682825348","https://openalex.org/W6713727690"],"related_works":["https://openalex.org/W2064951931","https://openalex.org/W2893763841","https://openalex.org/W2312116756","https://openalex.org/W2778699561","https://openalex.org/W2384122842","https://openalex.org/W2765876051","https://openalex.org/W2380536744","https://openalex.org/W40124310","https://openalex.org/W2889045432","https://openalex.org/W2100982643"],"abstract_inverted_index":{"Probabilistic":[0],"linear":[1,84],"discriminant":[2],"analysis":[3],"(PLDA)":[4],"is":[5,30,41,51,124],"a":[6,72,83,87,126],"popular":[7],"normalization":[8],"approach":[9,76,113],"for":[10],"the":[11,26,48,56,59,79,90,102,111,122],"i-vector":[12],"model,":[13,28],"and":[14,65,94],"has":[15],"delivered":[16],"state-of-the-art":[17],"performance":[18],"in":[19,45],"speaker":[20,38],"recognition.":[21],"A":[22],"potential":[23],"problem":[24],"of":[25,58],"PLDA":[27],"however,":[29],"that":[31,89,107],"it":[32],"essentially":[33],"assumes":[34],"Gaussian":[35],"distributions":[36],"over":[37],"vectors,":[39],"which":[40],"not":[42,52],"always":[43],"true":[44,63],"practice.":[46],"Additionally,":[47],"objective":[49],"function":[50],"directly":[53],"related":[54],"to":[55,77,109],"goal":[57],"task,":[60],"e.g.,":[61],"discriminating":[62],"speakers":[64],"imposters.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70],"propose":[71],"max-margin":[73],"metric":[74],"learning":[75],"solve":[78],"problems.":[80],"It":[81],"learns":[82],"transform":[85],"with":[86],"criterion":[88],"margin":[91],"between":[92],"target":[93],"imposter":[95],"trials":[96],"are":[97],"maximized.":[98],"Experiments":[99],"conducted":[100],"on":[101],"SRE08":[103],"core":[104],"test":[105],"show":[106],"compared":[108],"PLDA,":[110],"new":[112],"can":[114],"obtain":[115],"comparable":[116],"or":[117],"even":[118],"better":[119],"performance,":[120],"though":[121],"scoring":[123],"simply":[125],"cosine":[127],"computation.":[128]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}