{"id":"https://openalex.org/W4392903919","doi":"https://doi.org/10.1109/icassp48485.2024.10446161","title":"Asymmetric Clean Segments-Guided Self-Supervised Learning for Robust Speaker Verification","display_name":"Asymmetric Clean Segments-Guided Self-Supervised Learning for Robust Speaker Verification","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903919","doi":"https://doi.org/10.1109/icassp48485.2024.10446161"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5104260046","display_name":"Chong-Xin Gan","orcid":null},"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":"Chong-Xin Gan","raw_affiliation_strings":["The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,Hong Kong SAR","Dept. of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Dept. of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong SAR","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,Dept. of Electrical and Electronic Engineering,Hong Kong SAR","Dept. of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Dept. of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090644975","display_name":"Weiwei Lin","orcid":"https://orcid.org/0000-0002-9241-0271"},"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":"Weiwei Lin","raw_affiliation_strings":["The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,Hong Kong SAR","Dept. of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Dept. of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Inst. of Electrical and Computer Engineering,Taiwan","Inst. of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Inst. of Electrical and Computer Engineering,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Inst. of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5104260046"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":1.0911,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79350791,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"11081","last_page":"11085"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9983999729156494,"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":0.9929999709129333,"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":0.8242043256759644},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7520333528518677},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5779052972793579},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5667256116867065},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5411126017570496},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5164254307746887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48570284247398376},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4825022220611572},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4234822392463684},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35303497314453125},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17053672671318054},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09257394075393677}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8242043256759644},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7520333528518677},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5779052972793579},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5667256116867065},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5411126017570496},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5164254307746887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48570284247398376},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4825022220611572},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4234822392463684},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35303497314453125},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17053672671318054},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09257394075393677},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"},{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2121812409","https://openalex.org/W2141373863","https://openalex.org/W2150769028","https://openalex.org/W2154278880","https://openalex.org/W2219249508","https://openalex.org/W2587150483","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2747238065","https://openalex.org/W2793459270","https://openalex.org/W2808631503","https://openalex.org/W2888968865","https://openalex.org/W2890964092","https://openalex.org/W2962788625","https://openalex.org/W2972986505","https://openalex.org/W3015734344","https://openalex.org/W3024869864","https://openalex.org/W3025075133","https://openalex.org/W3026092005","https://openalex.org/W3035524453","https://openalex.org/W3039832962","https://openalex.org/W3090114880","https://openalex.org/W3116256056","https://openalex.org/W3160397447","https://openalex.org/W3161606033","https://openalex.org/W3205635414","https://openalex.org/W4287635082","https://openalex.org/W4295789112","https://openalex.org/W4296068987","https://openalex.org/W4375869145","https://openalex.org/W4394665180","https://openalex.org/W6688816777","https://openalex.org/W6774314701","https://openalex.org/W6777179611","https://openalex.org/W6781834539","https://openalex.org/W6783961830","https://openalex.org/W6783990618","https://openalex.org/W6784330115","https://openalex.org/W6864750640"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W3021676282","https://openalex.org/W3008176773"],"abstract_inverted_index":{"Contrastive":[0],"self-supervised":[1],"learning":[2],"(CSL)":[3],"for":[4],"speaker":[5,60],"verification":[6],"(SV)":[7],"has":[8],"drawn":[9],"increasing":[10],"interest":[11],"recently":[12],"due":[13],"to":[14,17,49,57,87,92,105],"its":[15],"ability":[16],"exploit":[18],"unlabeled":[19],"data.":[20],"Performing":[21],"data":[22],"augmentation":[23],"on":[24,120],"raw":[25],"waveforms,":[26],"such":[27],"as":[28],"adding":[29],"noise":[30],"or":[31],"reverberation,":[32],"plays":[33],"a":[34,68,129],"pivotal":[35],"role":[36],"in":[37,41],"achieving":[38],"promising":[39],"results":[40,119],"SV.":[42],"Data":[43],"augmentation,":[44],"however,":[45],"demands":[46],"meticulous":[47],"calibration":[48],"ensure":[50],"intact":[51],"speaker-specific":[52],"information,":[53],"which":[54],"is":[55,103],"difficult":[56],"achieve":[58,128],"without":[59],"labels.":[61],"To":[62],"address":[63],"this":[64],"issue,":[65],"we":[66],"introduce":[67],"novel":[69],"framework":[70,126],"by":[71],"incorporating":[72],"clean":[73,83,111],"and":[74,96,112,137],"augmented":[75,113],"segments":[76,84,91],"into":[77],"the":[78,100,107,110,124,134],"contrastive":[79,101],"training":[80],"pipeline.":[81],"The":[82],"are":[85],"repurposed":[86],"pair":[88],"with":[89],"noisy":[90],"form":[93],"additional":[94],"positive":[95],"negative":[97],"pairs.":[98],"Moreover,":[99],"loss":[102],"weighted":[104],"increase":[106],"difference":[108],"between":[109],"embeddings":[114],"of":[115],"different":[116],"speakers.":[117],"Experimental":[118],"Voxceleb1":[121],"suggest":[122],"that":[123],"proposed":[125],"can":[127],"remarkable":[130],"19%":[131],"improvement":[132],"over":[133],"conventional":[135],"methods,":[136],"it":[138],"surpasses":[139],"many":[140],"existing":[141],"state-of-the-art":[142],"techniques.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
