{"id":"https://openalex.org/W4375869145","doi":"https://doi.org/10.1109/icassp49357.2023.10096230","title":"Discriminative Speaker Representation Via Contrastive Learning with Class-Aware Attention in Angular Space","display_name":"Discriminative Speaker Representation Via Contrastive Learning with Class-Aware Attention in Angular Space","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869145","doi":"https://doi.org/10.1109/icassp49357.2023.10096230"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5100356635","display_name":"Zhe Li","orcid":"https://orcid.org/0000-0002-0519-7434"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Zhe Li","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electronic and Information Engineering","Department of Electronic and Information Engineering, The Hong Kong Polytechnic University"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electronic and Information Engineering","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Electronic and Information Engineering, The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electronic and Information Engineering","Department of Electronic and Information Engineering, The Hong Kong Polytechnic University"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electronic and Information Engineering","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Electronic and Information Engineering, The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helen Mei-Ling Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management","Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100356635"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":1.9658,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88674608,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9997000098228455,"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":0.9983000159263611,"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":0.8285443782806396},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8194615840911865},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6755823493003845},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.646729588508606},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5927554368972778},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5921480059623718},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.524456262588501},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5231565237045288},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46981197595596313},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4556586444377899},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4164118766784668},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3423234820365906},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2897005081176758},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.21674245595932007}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8285443782806396},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8194615840911865},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6755823493003845},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.646729588508606},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5927554368972778},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5921480059623718},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.524456262588501},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5231565237045288},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46981197595596313},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4556586444377899},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4164118766784668},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3423234820365906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2897005081176758},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.21674245595932007},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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","id":"https://metadata.un.org/sdg/10","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2096733369","https://openalex.org/W2519373641","https://openalex.org/W2784163702","https://openalex.org/W2798991696","https://openalex.org/W2936774411","https://openalex.org/W2950673314","https://openalex.org/W2962788625","https://openalex.org/W2962798895","https://openalex.org/W2969985801","https://openalex.org/W3005680577","https://openalex.org/W3024869864","https://openalex.org/W3035524453","https://openalex.org/W3103152812","https://openalex.org/W3118062200","https://openalex.org/W3152426975","https://openalex.org/W3156636935","https://openalex.org/W3160397447","https://openalex.org/W3160646455","https://openalex.org/W3161606033","https://openalex.org/W3173783447","https://openalex.org/W3175362188","https://openalex.org/W3201363892","https://openalex.org/W3205519288","https://openalex.org/W3206886023","https://openalex.org/W4200633018","https://openalex.org/W4220961503","https://openalex.org/W4226090390","https://openalex.org/W4283022413","https://openalex.org/W4285296644","https://openalex.org/W4287812705","https://openalex.org/W4295539426","https://openalex.org/W4312095959","https://openalex.org/W6748666111","https://openalex.org/W6754005058","https://openalex.org/W6770717842","https://openalex.org/W6774314701","https://openalex.org/W6776700526","https://openalex.org/W6778102432","https://openalex.org/W6795205085","https://openalex.org/W6806079149"],"related_works":["https://openalex.org/W3095152779","https://openalex.org/W3128220219","https://openalex.org/W2982889384","https://openalex.org/W4226227567","https://openalex.org/W2971218105","https://openalex.org/W3006353185","https://openalex.org/W3010284783","https://openalex.org/W4287113729","https://openalex.org/W3173314472","https://openalex.org/W3119773509"],"abstract_inverted_index":{"The":[0],"challenges":[1],"in":[2,51],"applying":[3],"contrastive":[4,14,37,49,82,95],"learning":[5,38,107],"to":[6,79,90,113],"speaker":[7,57,121],"verification":[8],"(SV)":[9],"are":[10],"that":[11,20,104,118],"the":[12,21,31,47,53,56,62,80,92,111],"softmax-based":[13],"loss":[15,50],"lacks":[16],"discriminative":[17],"power":[18],"and":[19,94,101],"hard":[22,73],"negative":[23,74],"pairs":[24],"can":[25,109],"easily":[26],"influence":[27],"learning.":[28],"To":[29],"overcome":[30],"first":[32],"challenge,":[33,64],"we":[34,65],"propose":[35],"a":[36,67],"SV":[39],"framework":[40],"incorporating":[41],"an":[42,115],"additive":[43],"angular":[44],"margin":[45,54],"into":[46],"supervised":[48,81],"which":[52,72],"improves":[55],"representation\u2019s":[58],"discrimination":[59,122],"ability.":[60],"For":[61],"second":[63],"introduce":[66],"class-aware":[68],"attention":[69],"mechanism":[70],"through":[71],"samples":[75],"contribute":[76],"less":[77],"significantly":[78],"loss.":[83,96],"We":[84],"also":[85],"employed":[86],"gradient-based":[87],"multi-objective":[88],"optimization":[89],"balance":[91],"classification":[93],"Experimental":[97],"results":[98],"on":[99],"CN-Celeb":[100],"Voxceleb1":[102],"show":[103],"this":[105],"new":[106],"objective":[108],"cause":[110],"encoder":[112],"find":[114],"embedding":[116],"space":[117],"exhibits":[119],"great":[120],"across":[123],"languages.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2025-10-10T00:00:00"}