{"id":"https://openalex.org/W4394744939","doi":"https://doi.org/10.1109/taslp.2024.3385277","title":"<i>Golden Gemini</i> is All You Need: Finding the Sweet Spots for Speaker Verification","display_name":"<i>Golden Gemini</i> is All You Need: Finding the Sweet Spots for Speaker Verification","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4394744939","doi":"https://doi.org/10.1109/taslp.2024.3385277"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3385277","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3385277","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10497864.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10497864.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013047791","display_name":"Tianchi Liu","orcid":"https://orcid.org/0000-0003-3472-0703"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tianchi Liu","raw_affiliation_strings":["Institute for Infocomm Research (I<sup>2</sup>R), Agency for Science, Technology and Research (A*STAR), Singapore","Department of Electrical and Computer Engineering, National University of Singapore, Singapore","Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Singapore"],"raw_orcid":"https://orcid.org/0000-0003-3472-0703","affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I<sup>2</sup>R), Agency for Science, Technology and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004287909","display_name":"Kong Aik Lee","orcid":"https://orcid.org/0000-0001-9133-3000"},"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":"Kong Aik Lee","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Hong Kong Polytechnic University, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-9133-3000","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101991100","display_name":"Qiongqiong Wang","orcid":"https://orcid.org/0000-0002-9903-0618"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qiongqiong Wang","raw_affiliation_strings":["Institute for Infocomm Research (I<sup>2</sup>R), Agency for Science, Technology and Research (A*STAR), Singapore","Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Singapore"],"raw_orcid":"https://orcid.org/0000-0002-9903-0618","affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I<sup>2</sup>R), Agency for Science, Technology and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Shenzhen Research Institute of Big Data, School of Data Science, Chinese University of Hong Kong, Shenzhen, China","Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-9158-9401","affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, School of Data Science, Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.6565,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.96350715,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"2324","last_page":"2337"},"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":0.9991999864578247,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9972000122070312,"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":0.6084641218185425},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.5619511604309082},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5427685976028442},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4703284204006195},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3418395221233368},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3335641026496887}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6084641218185425},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.5619511604309082},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5427685976028442},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4703284204006195},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3418395221233368},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3335641026496887},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2024.3385277","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3385277","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10497864.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/109492","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/109492","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/109492/1/Liu_Golden_Gemini_All.pdf","source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal/Magazine Article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2024.3385277","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3385277","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10497864.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2799040894","display_name":null,"funder_award_id":"62271432","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5088964179","display_name":null,"funder_award_id":"T00120220002","funder_id":"https://openalex.org/F4320331102","funder_display_name":"Shenzhen Research Institute of Big Data"}],"funders":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320331102","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89"},{"id":"https://openalex.org/F4320333998","display_name":"Shenzhen Research Institute, City University of Hong Kong","ror":"https://ror.org/00xc0ma20"},{"id":"https://openalex.org/F4320334744","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394744939.pdf","grobid_xml":"https://content.openalex.org/works/W4394744939.grobid-xml"},"referenced_works_count":101,"referenced_works":["https://openalex.org/W1987841215","https://openalex.org/W1996512145","https://openalex.org/W2121812409","https://openalex.org/W2123768812","https://openalex.org/W2124641009","https://openalex.org/W2129244720","https://openalex.org/W2194775991","https://openalex.org/W2402146185","https://openalex.org/W2516764878","https://openalex.org/W2549139847","https://openalex.org/W2587150483","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2747165665","https://openalex.org/W2748488820","https://openalex.org/W2752782242","https://openalex.org/W2775795276","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2928165649","https://openalex.org/W2936774411","https://openalex.org/W2938358845","https://openalex.org/W2964054038","https://openalex.org/W2969985801","https://openalex.org/W2973003853","https://openalex.org/W2973190269","https://openalex.org/W3013020904","https://openalex.org/W3015598461","https://openalex.org/W3024869864","https://openalex.org/W3096918678","https://openalex.org/W3097073596","https://openalex.org/W3097653961","https://openalex.org/W3126634788","https://openalex.org/W3135006803","https://openalex.org/W3136330474","https://openalex.org/W3138516171","https://openalex.org/W3141035251","https://openalex.org/W3142516134","https://openalex.org/W3152426975","https://openalex.org/W3162347631","https://openalex.org/W3162784934","https://openalex.org/W3163421828","https://openalex.org/W3163505255","https://openalex.org/W3167533889","https://openalex.org/W3174649707","https://openalex.org/W3196649213","https://openalex.org/W3205519288","https://openalex.org/W3206287456","https://openalex.org/W4205654098","https://openalex.org/W4214698081","https://openalex.org/W4220961503","https://openalex.org/W4221154745","https://openalex.org/W4221154746","https://openalex.org/W4223531842","https://openalex.org/W4224256913","https://openalex.org/W4224916451","https://openalex.org/W4224916733","https://openalex.org/W4224920133","https://openalex.org/W4225682608","https://openalex.org/W4288091954","https://openalex.org/W4296068762","https://openalex.org/W4312443924","https://openalex.org/W4315778293","https://openalex.org/W4319862221","https://openalex.org/W4323022270","https://openalex.org/W4372260240","https://openalex.org/W4372260481","https://openalex.org/W4372271885","https://openalex.org/W4372340947","https://openalex.org/W4372348046","https://openalex.org/W4375798879","https://openalex.org/W4375868885","https://openalex.org/W4375868932","https://openalex.org/W4375868968","https://openalex.org/W4375868975","https://openalex.org/W4375869221","https://openalex.org/W4375869294","https://openalex.org/W4377864567","https://openalex.org/W4381232968","https://openalex.org/W4381747927","https://openalex.org/W4385822320","https://openalex.org/W4385822752","https://openalex.org/W4385822954","https://openalex.org/W4385823321","https://openalex.org/W4385823425","https://openalex.org/W4385823498","https://openalex.org/W4396982346","https://openalex.org/W6631190155","https://openalex.org/W6713727690","https://openalex.org/W6747218270","https://openalex.org/W6757817989","https://openalex.org/W6769178842","https://openalex.org/W6784245331","https://openalex.org/W6798523648","https://openalex.org/W6800698692","https://openalex.org/W6850780009","https://openalex.org/W6852751821","https://openalex.org/W6857495872"],"related_works":["https://openalex.org/W4315697128","https://openalex.org/W3102845713","https://openalex.org/W2971502891","https://openalex.org/W3205506801","https://openalex.org/W4280599700","https://openalex.org/W2051487156","https://openalex.org/W3183570023","https://openalex.org/W4382323155","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"The":[0,75],"residual":[1],"neural":[2],"networks":[3],"(ResNet)":[4],"demonstrate":[5],"the":[6,16,23,32,42,65,85,93,101,130,165,187,190,211],"impressive":[7],"performance":[8,140],"in":[9,50],"automatic":[10],"speaker":[11],"verification":[12],"(ASV).":[13],"They":[14],"treat":[15],"time":[17,45],"and":[18,34,46,57,89,145,161,171,202,223],"frequency":[19,47,71,90],"dimensions":[20],"equally,":[21],"following":[22,129],"default":[24],"stride":[25,102],"configuration":[26],"designed":[27],"for":[28,73,122],"image":[29],"recognition,":[30],"where":[31],"horizontal":[33],"vertical":[35],"axes":[36],"exhibit":[37],"similarities.":[38],"This":[39],"approach":[40],"ignores":[41],"fact":[43],"that":[44],"are":[48,226],"asymmetric":[49],"speech":[51],"representation.":[52],"We":[53,104,175],"address":[54],"this":[55],"issue":[56],"postulate":[58],"<italic":[59,111,180,192,212,220],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[60,112,181,193,213,221],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Golden-Gemini":[61],"Hypothesis,</i>":[62],"which":[63,116],"posits":[64],"prioritization":[66],"of":[67,87,167,189],"temporal":[68,88],"resolution":[69,72],"over":[70],"ASV.":[74],"hypothesis":[76],"is":[77],"verified":[78],"by":[79,169,173],"conducting":[80],"a":[81,96,119,132,138,207,217],"systematic":[82],"study":[83],"on":[84,92,142],"impact":[86],"resolutions":[91],"performance,":[94],"using":[95,216],"trellis":[97],"diagram":[98],"to":[99,177],"represent":[100],"space.":[103],"further":[105],"identify":[106],"two":[107],"optimal":[108],"points,":[109],"namely":[110,210],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Golden":[113,194],"Gemini</i>":[114,195],",":[115],"serves":[117],"as":[118,179],"guiding":[120],"principle":[121],"designing":[123],"2D":[124],"ResNet-based":[125],"ASV":[126],"models.":[127],"By":[128],"principle,":[131],"state-of-the-art":[133],"ResNet":[134],"baseline":[135],"model":[136],"gains":[137],"significant":[139],"improvement":[141],"VoxCeleb,":[143],"SITW,":[144],"CNCeleb":[146],"datasets":[147],"with":[148],"7.70%/11.76%":[149],"average":[150],"EER/minDCF":[151],"reductions,":[152],"respectively,":[153],"across":[154,198],"different":[155],"network":[156],"depths":[157],"(ResNet18,":[158],"34,":[159],"50,":[160],"101),":[162],"while":[163],"reducing":[164],"number":[166],"parameters":[168],"16.5%":[170],"FLOPs":[172],"4.1%.":[174],"refer":[176],"it":[178],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Gemini</i>":[182,214],"ResNet.":[183],"Further":[184],"investigation":[185],"reveals":[186],"efficacy":[188],"proposed":[191],"operating":[196],"points":[197],"various":[199],"training":[200],"conditions":[201],"architectures.":[203],"Furthermore,":[204],"we":[205],"present":[206],"new":[208],"benchmark,":[209],"DF-ResNet,":[215],"cutting-edge":[218],"model.":[219],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Codes":[222],"pre-trained":[224],"models":[225],"available":[227],"at":[228],"<uri>https://github.com/Tianchi-Liu9/Golden-Gemini-for-Speaker-Verification</uri>.</i>":[229]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":6}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2024-04-13T00:00:00"}