{"id":"https://openalex.org/W4289792473","doi":"https://doi.org/10.1109/jstsp.2022.3196562","title":"L-Mix: A Latent-Level Instance Mixup Regularization for Robust Self-Supervised Speaker Representation Learning","display_name":"L-Mix: A Latent-Level Instance Mixup Regularization for Robust Self-Supervised Speaker Representation Learning","publication_year":2022,"publication_date":"2022-08-04","ids":{"openalex":"https://openalex.org/W4289792473","doi":"https://doi.org/10.1109/jstsp.2022.3196562"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2022.3196562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3196562","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal Processing","raw_type":"journal-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/A5082739860","display_name":"Woo Hyun Kang","orcid":"https://orcid.org/0000-0001-8739-9349"},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Woo Hyun Kang","raw_affiliation_strings":["Computer Research Institute of Montreal, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0001-8739-9349","affiliations":[{"raw_affiliation_string":"Computer Research Institute of Montreal, Montreal, Canada","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055570520","display_name":"Jahangir Alam","orcid":"https://orcid.org/0000-0003-1081-3665"},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jahangir Alam","raw_affiliation_strings":["Computer Research Institute of Montreal, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0003-1081-3665","affiliations":[{"raw_affiliation_string":"Computer Research Institute of Montreal, Montreal, Canada","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066980762","display_name":"Abderrahim Fathan","orcid":"https://orcid.org/0000-0002-5749-1643"},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Abderrahim Fathan","raw_affiliation_strings":["Computer Research Institute of Montreal, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0002-5749-1643","affiliations":[{"raw_affiliation_string":"Computer Research Institute of Montreal, Montreal, Canada","institution_ids":["https://openalex.org/I4210111842"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210111842"],"apc_list":{"value":2195,"currency":"USD","value_usd":2195},"apc_paid":null,"fwci":2.6901,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.91074641,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"16","issue":"6","first_page":"1263","last_page":"1272"},"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":0.9970999956130981,"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":0.9894999861717224,"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":0.7062262296676636},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.658861517906189},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6139092445373535},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5372981429100037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5369138121604919},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5296152830123901},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46640744805336},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4315497875213623},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4259694516658783},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.4255516231060028},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4097343683242798},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1999981701374054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7062262296676636},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.658861517906189},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6139092445373535},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5372981429100037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5369138121604919},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5296152830123901},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46640744805336},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4315497875213623},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4259694516658783},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.4255516231060028},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4097343683242798},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1999981701374054}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2022.3196562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3196562","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.550000011920929}],"awards":[{"id":"https://openalex.org/G270585729","display_name":"Robust Speaker Verification in Real Application Scenarios","funder_award_id":"rgpin-2019-05381","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1936725236","https://openalex.org/W2035890032","https://openalex.org/W2101234009","https://openalex.org/W2141245797","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2752782242","https://openalex.org/W2784163702","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2936774411","https://openalex.org/W3000000254","https://openalex.org/W3013020904","https://openalex.org/W3024869864","https://openalex.org/W3042558177","https://openalex.org/W3086452730","https://openalex.org/W3091002423","https://openalex.org/W3094325190","https://openalex.org/W3103152812","https://openalex.org/W3160397447","https://openalex.org/W3161606033","https://openalex.org/W3163839574","https://openalex.org/W3166898278","https://openalex.org/W3199161700","https://openalex.org/W3206523078","https://openalex.org/W4287635082","https://openalex.org/W4307823382","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6640963894","https://openalex.org/W6675354045","https://openalex.org/W6713414053","https://openalex.org/W6754184789","https://openalex.org/W6760184523","https://openalex.org/W6772379172","https://openalex.org/W6779230768","https://openalex.org/W6781368565","https://openalex.org/W6783527727","https://openalex.org/W6784256521","https://openalex.org/W6784330115","https://openalex.org/W6791713434"],"related_works":["https://openalex.org/W1586607209","https://openalex.org/W122912556","https://openalex.org/W4312414840","https://openalex.org/W2621411691","https://openalex.org/W2271357838","https://openalex.org/W2556866732","https://openalex.org/W2794908468","https://openalex.org/W2328989934","https://openalex.org/W2348322200","https://openalex.org/W2515319207"],"abstract_inverted_index":{"Over":[0],"the":[1,18,25,32,39,59,87,90,113,118,126,129,136,148,152,158,166],"recent":[2],"years,":[3],"various":[4],"self-supervised":[5,19,61,98,137,159],"embedding":[6,44,63,100,160],"learning":[7,20],"methods":[8],"for":[9,95],"deep":[10],"speaker":[11,36,43,62,99,177],"verification":[12,178],"were":[13,133,145],"proposed.":[14],"The":[15],"performance":[16],"of":[17,35,89,117,173],"framework":[21],"highly":[22],"depends":[23],"on":[24,47,112,147],"data":[26],"augmentation":[27],"technique,":[28],"but":[29],"due":[30],"to":[31,72,74,81],"sensitive":[33],"nature":[34],"information":[37],"within":[38],"speech":[40],"signal,":[41],"most":[42],"training":[45,96,174],"relies":[46],"simple":[48],"augmentations":[49],"such":[50],"as":[51],"additive":[52],"noise":[53],"or":[54],"simulated":[55],"reverberation.":[56],"Thus":[57],"while":[58],"conventional":[60],"systems":[64],"can":[65,162],"yield":[66],"minimum":[67],"within-utterance":[68],"variability,":[69],"their":[70],"capability":[71],"generalize":[73],"out-of-set":[75],"utterance":[76],"is":[77],"limited.":[78],"In":[79,123],"order":[80],"alleviate":[82],"this":[83,124],"problem,":[84],"we":[85,103,155],"investigate":[86],"utilization":[88],"instance":[91],"mix":[92],"(i-mix)":[93],"regularization":[94],"a":[97,105],"system.":[101],"Moreover,":[102],"propose":[104],"new":[106],"mixup":[107],"strategy":[108,132],"that":[109,157],"applies":[110],"i-mix":[111,127,167],"latent":[114],"space,":[115],"instead":[116],"raw":[119],"acoustic":[120],"feature":[121],"domain.":[122],"paper,":[125],"and":[128,140,144,168,176],"proposed":[130],"l-mix":[131,169],"incorporated":[134],"into":[135],"angular":[138],"prototypical":[139],"softmax-based":[141],"objective":[142],"functions":[143],"evaluated":[146],"VoxCeleb":[149],"dataset.":[150],"From":[151],"experimental":[153],"results,":[154],"observe":[156],"network":[161],"benefit":[163],"greatly":[164],"from":[165],"strategies":[170],"in":[171],"terms":[172],"stability":[175],"performance.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}