{"id":"https://openalex.org/W4372271607","doi":"https://doi.org/10.1109/icassp49357.2023.10095066","title":"DASA: Difficulty-Aware Semantic Augmentation for Speaker Verification","display_name":"DASA: Difficulty-Aware Semantic Augmentation for Speaker Verification","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372271607","doi":"https://doi.org/10.1109/icassp49357.2023.10095066"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095066","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/A5103325935","display_name":"Yuanyuan Wang","orcid":"https://orcid.org/0000-0003-1367-0989"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":true,"raw_author_name":"Yuanyuan Wang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354801","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0003-3383-7889"},"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"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"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"]},{"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"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024368167","display_name":"Zhihan Yang","orcid":"https://orcid.org/0009-0004-1659-1404"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Zhihan Yang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012261926","display_name":"Tao Wei","orcid":"https://orcid.org/0000-0002-6549-3999"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Wei","raw_affiliation_strings":["Ping An Technology,Shenzhen,China","Ping An Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101570585","display_name":"Kun Zou","orcid":"https://orcid.org/0009-0008-0575-5142"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Zou","raw_affiliation_strings":["Ping An Technology,Shenzhen,China","Ping An Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4401726822"]}]},{"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 Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5103325935"],"corresponding_institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04055985,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.9991000294685364,"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":0.9969000220298767,"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":0.8307373523712158},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7381818294525146},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5915727615356445},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5426192879676819},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5410415530204773},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4844539165496826},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.4691794216632843},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4596940577030182},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4083099365234375},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.39480215311050415},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37627169489860535},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3635367751121521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3562471866607666},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3433712124824524},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21439921855926514},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20261460542678833}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8307373523712158},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7381818294525146},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5915727615356445},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5426192879676819},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5410415530204773},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4844539165496826},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4691794216632843},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4596940577030182},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4083099365234375},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.39480215311050415},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37627169489860535},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3635367751121521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3562471866607666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3433712124824524},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21439921855926514},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20261460542678833},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095066","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1936725236","https://openalex.org/W2046056978","https://openalex.org/W2194775991","https://openalex.org/W2407080277","https://openalex.org/W2726515241","https://openalex.org/W2784163702","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2936774411","https://openalex.org/W2944613371","https://openalex.org/W2970941190","https://openalex.org/W2972668418","https://openalex.org/W2973190269","https://openalex.org/W2976816191","https://openalex.org/W3010925296","https://openalex.org/W3015598461","https://openalex.org/W3015611708","https://openalex.org/W3024869864","https://openalex.org/W3095079700","https://openalex.org/W3103152812","https://openalex.org/W3126121388","https://openalex.org/W3134490682","https://openalex.org/W3177230409","https://openalex.org/W3201565470","https://openalex.org/W4206908380","https://openalex.org/W4221154745","https://openalex.org/W4283458492","https://openalex.org/W6764733053","https://openalex.org/W6767312631","https://openalex.org/W6780927959"],"related_works":["https://openalex.org/W2982889384","https://openalex.org/W4226227567","https://openalex.org/W2971218105","https://openalex.org/W4287113729","https://openalex.org/W3173314472","https://openalex.org/W3103152812","https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W4235705411","https://openalex.org/W1996621592"],"abstract_inverted_index":{"Data":[0],"augmentation":[1,17,44],"is":[2],"vital":[3],"to":[4,104,118],"the":[5,23,30,112,127,140],"generalization":[6],"ability":[7],"and":[8,29,120,135],"robustness":[9],"of":[10,114,126],"deep":[11],"neural":[12],"networks":[13],"(DNNs)":[14],"models.":[15],"Existing":[16],"methods":[18],"for":[19,47],"speaker":[20,48,57,72,92,107],"verification":[21],"manipulate":[22],"raw":[24],"signal,":[25],"which":[26,50,77,132],"are":[27,78,88],"time-consuming":[28],"augmented":[31,115],"samples":[32,55,69,116],"lack":[33],"diversity.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,66,97,110],"present":[39],"a":[40,122,145,153],"novel":[41],"difficulty-aware":[42,99],"semantic":[43,75],"(DASA)":[45],"approach":[46,142],"verification,":[49],"can":[51,143],"generate":[52],"diversified":[53],"training":[54,68],"in":[56,157],"embedding":[58],"space":[59],"with":[60,130],"negligible":[61],"extra":[62],"computing":[63],"cost.":[64],"Firstly,":[65],"augment":[67],"by":[70],"perturbing":[71],"embeddings":[73,93],"along":[74],"directions,":[76],"obtained":[79],"from":[80,90],"speaker-wise":[81],"covariance":[82,86],"matrices.":[83],"Secondly,":[84],"accurate":[85],"matrices":[87],"estimated":[89],"robust":[91],"during":[94],"training,":[95],"so":[96],"introduce":[98],"additive":[100],"margin":[101],"softmax":[102],"(DAAM-Softmax)":[103],"obtain":[105],"optimal":[106],"embeddings.":[108],"Finally,":[109],"assume":[111],"number":[113],"goes":[117],"infinity":[119],"derive":[121],"closed-form":[123],"upper":[124],"bound":[125],"expected":[128],"loss":[129],"DASA,":[131],"achieves":[133,152],"compatibility":[134],"efficiency.":[136],"Extensive":[137],"experiments":[138],"demonstrate":[139],"proposed":[141],"achieve":[144],"remarkable":[146],"performance":[147],"improvement.":[148],"The":[149],"best":[150],"result":[151],"14.6%":[154],"relative":[155],"reduction":[156],"EER":[158],"metric":[159],"on":[160],"CN-Celeb":[161],"evaluation":[162],"set.":[163]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}