{"id":"https://openalex.org/W4405709112","doi":"https://doi.org/10.1109/iscslp63861.2024.10800510","title":"Optimizing Deep Speaker Embeddings with a Dynamic Cross Triplet Framework","display_name":"Optimizing Deep Speaker Embeddings with a Dynamic Cross Triplet Framework","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709112","doi":"https://doi.org/10.1109/iscslp63861.2024.10800510"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800510","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th 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/A5100783142","display_name":"Li Jin","orcid":"https://orcid.org/0000-0001-8833-4862"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Li","raw_affiliation_strings":["University of Science and Technology of China,Hefei"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lirong Dai","raw_affiliation_strings":["University of Science and Technology of China,Hefei"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"378","last_page":"382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.996999979019165,"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":0.977400004863739,"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":0.7220556735992432},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5598599910736084},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4593541622161865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3813554644584656},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.35915452241897583}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7220556735992432},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5598599910736084},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4593541622161865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3813554644584656},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.35915452241897583}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800510","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1517437533","display_name":null,"funder_award_id":"12204200","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G447375254","display_name":null,"funder_award_id":"2022YFF0608503","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2096733369","https://openalex.org/W2194775991","https://openalex.org/W2598634450","https://openalex.org/W2620998106","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2784163702","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2936774411","https://openalex.org/W2962898354","https://openalex.org/W2969985801","https://openalex.org/W3013020904","https://openalex.org/W3015611708","https://openalex.org/W3024869864","https://openalex.org/W3096431026","https://openalex.org/W3163421828","https://openalex.org/W3174864715","https://openalex.org/W3198161435","https://openalex.org/W4297841827","https://openalex.org/W6769178842"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W66821593","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W1521299571","https://openalex.org/W4313854686","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W1516392727","https://openalex.org/W2140022733"],"abstract_inverted_index":{"Data":[0],"augmentation":[1],"is":[2,36,101],"recognized":[3],"as":[4],"a":[5,67],"powerful":[6],"technique":[7],"for":[8,45],"enhancing":[9],"the":[10,24,30,40,46,56,94,115,120,123],"robustness":[11],"of":[12,122],"speaker":[13,84],"verification":[14],"systems.":[15],"However,":[16],"this":[17,50,63,75],"method":[18,76],"can":[19,52],"lead":[20],"to":[21,37,92,109],"discrepancies":[22],"between":[23],"training":[25,98],"and":[26,42,74,80,86,104],"inference":[27],"phases":[28],"in":[29],"feature":[31,60],"domain.":[32],"A":[33],"common":[34],"solution":[35],"simply":[38],"combine":[39],"original":[41],"augmented":[43],"data":[44],"network":[47],"optimization.":[48],"Unfortunately,":[49],"approach":[51],"not":[53],"fully":[54],"utilize":[55],"information":[57],"across":[58,90],"different":[59],"domains.":[61],"In":[62],"paper,":[64],"we":[65],"introduce":[66],"novel":[68],"Dynamic":[69],"Cross":[70],"Triplet":[71],"(DCT)":[72],"method,":[73],"initially":[77],"measures":[78],"intra-domain":[79],"inter-domain":[81],"similarities":[82],"using":[83],"embeddings,":[85],"then":[87],"transfers":[88],"them":[89],"domains":[91],"address":[93],"mismatch":[95],"issue.":[96],"Notably,":[97],"with":[99],"DCT":[100,125],"both":[102],"efficient":[103],"effective,":[105],"making":[106],"it":[107],"applicable":[108],"various":[110],"networks.":[111],"Experimental":[112],"results":[113],"on":[114],"benchmark":[116],"Voxceleb":[117],"dataset":[118],"demonstrate":[119],"superiority":[121],"proposed":[124],"method.":[126]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}