{"id":"https://openalex.org/W3007997916","doi":"https://doi.org/10.1109/asru46091.2019.9003794","title":"Optimizing Neural Network Embeddings Using a Pair-Wise Loss for Text-Independent Speaker Verification","display_name":"Optimizing Neural Network Embeddings Using a Pair-Wise Loss for Text-Independent Speaker Verification","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007997916","doi":"https://doi.org/10.1109/asru46091.2019.9003794","mag":"3007997916"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003794","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5074132219","display_name":"Hira Dhamyal","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hira Dhamyal","raw_affiliation_strings":["Language Technology Institute, Carnegie Mellon University, Pittsburgh, United States"],"affiliations":[{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103218426","display_name":"Tianyan Zhou","orcid":"https://orcid.org/0000-0003-3238-2982"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyan Zhou","raw_affiliation_strings":["Language Technology Institute, Carnegie Mellon University, Pittsburgh, United States"],"affiliations":[{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113017615","display_name":"Bhiksha Raj","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhiksha Raj","raw_affiliation_strings":["Language Technology Institute, Carnegie Mellon University, Pittsburgh, United States"],"affiliations":[{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102775511","display_name":"Rita Singh","orcid":"https://orcid.org/0000-0003-3743-0162"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rita Singh","raw_affiliation_strings":["Language Technology Institute, Carnegie Mellon University, Pittsburgh, United States"],"affiliations":[{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5074132219"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.5601,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76360566,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"abs 1704 8063","issue":null,"first_page":"742","last_page":"748"},"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":0.9998000264167786,"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":0.9991999864578247,"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/speaker-verification","display_name":"Speaker verification","score":0.8164888024330139},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7668323516845703},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6563146114349365},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4996612071990967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45025834441185},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42311742901802063},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3229072391986847}],"concepts":[{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.8164888024330139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7668323516845703},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6563146114349365},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4996612071990967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45025834441185},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42311742901802063},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3229072391986847}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003794","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W111477576","https://openalex.org/W1480487340","https://openalex.org/W1563939609","https://openalex.org/W1614659291","https://openalex.org/W1972978214","https://openalex.org/W2046056978","https://openalex.org/W2106053110","https://openalex.org/W2121812409","https://openalex.org/W2129379984","https://openalex.org/W2135346934","https://openalex.org/W2138621090","https://openalex.org/W2147147599","https://openalex.org/W2148154194","https://openalex.org/W2157364932","https://openalex.org/W2194775991","https://openalex.org/W2290689761","https://openalex.org/W2395750323","https://openalex.org/W2401594978","https://openalex.org/W2467139031","https://openalex.org/W2520774990","https://openalex.org/W2587150483","https://openalex.org/W2606377603","https://openalex.org/W2612434969","https://openalex.org/W2745379946","https://openalex.org/W2748488820","https://openalex.org/W2889519245","https://openalex.org/W2890493389","https://openalex.org/W2890964092","https://openalex.org/W2962832278","https://openalex.org/W2963466847","https://openalex.org/W2963670602","https://openalex.org/W4245923654","https://openalex.org/W6604441197","https://openalex.org/W6675751002","https://openalex.org/W6696345733","https://openalex.org/W6736370658","https://openalex.org/W6754569177"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W1521299571","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W1516392727","https://openalex.org/W2140022733"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3],"new":[4],"loss":[5,10,72,114],"function":[6],"called":[7],"the":[8,12,16,30,33,36,68,75,84,87,92,97,104,110,113],"\u201cquartet\u201d":[9],"for":[11,19,38,61,64],"better":[13,39,65],"optimization":[14,34],"of":[15,35,67,80,112],"neural":[17,26,118],"networks":[18],"matching":[20],"tasks.":[21],"For":[22],"such":[23],"tasks,":[24],"where":[25],"network":[27,37],"embeddings":[28,40,44],"are":[29,45],"key":[31],"component,":[32],"is":[41],"critical.":[42],"The":[43,70],"required":[46],"to":[47],"be":[48],"class":[49,94,99],"discriminative,":[50],"resulting":[51],"in":[52],"minimal":[53],"inter-class":[54],"variation":[55,59],"and":[56,82,96,108],"maximal":[57],"intra-class":[58],"even":[60],"unseen":[62],"classes":[63],"generalization":[66],"network.":[69,119],"quartet":[71],"explicitly":[73],"computes":[74],"distance":[76],"metric":[77],"between":[78,86,91],"pairs":[79,95],"inputs":[81],"increases":[83],"gap":[85],"similarity":[88],"score":[89],"distributions":[90],"same":[93],"different":[98],"pairs.":[100],"We":[101],"evaluate":[102],"on":[103,115],"speaker":[105],"verification":[106],"task":[107],"demonstrate":[109],"performance":[111],"our":[116],"proposed":[117]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}