{"id":"https://openalex.org/W3163059624","doi":"https://doi.org/10.1109/icassp39728.2021.9414704","title":"Cam: Context-Aware Masking for Robust Speaker Verification","display_name":"Cam: Context-Aware Masking for Robust Speaker Verification","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163059624","doi":"https://doi.org/10.1109/icassp39728.2021.9414704","mag":"3163059624"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5005134850","display_name":"Ya-Qi Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ya-Qi Yu","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101700479","display_name":"Siqi Zheng","orcid":"https://orcid.org/0000-0002-5481-7900"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siqi Zheng","raw_affiliation_strings":["Speech Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Speech Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109630497","display_name":"Hongbin Suo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongbin Suo","raw_affiliation_strings":["Speech Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Speech Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101648572","display_name":"Yun Lei","orcid":"https://orcid.org/0000-0003-4572-6078"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Lei","raw_affiliation_strings":["Speech Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Speech Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101402002","display_name":"Wu-Jun Li","orcid":"https://orcid.org/0000-0003-2499-4006"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu-Jun Li","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5005134850"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":1.4956,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.85414947,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6703","last_page":"6707"},"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":0.9995999932289124,"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":0.9987000226974487,"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":0.8148154020309448},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7333784103393555},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6968928575515747},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6517874598503113},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.581336259841919},{"id":"https://openalex.org/keywords/lossy-compression","display_name":"Lossy compression","score":0.5457872152328491},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5322076678276062},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.48951852321624756},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.48226433992385864},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4678286910057068},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.46327921748161316},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.45102235674858093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4236021637916565},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.41456180810928345},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3438655138015747},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1305786669254303}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148154020309448},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7333784103393555},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6968928575515747},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6517874598503113},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.581336259841919},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.5457872152328491},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5322076678276062},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.48951852321624756},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.48226433992385864},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4678286910057068},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.46327921748161316},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.45102235674858093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4236021637916565},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41456180810928345},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3438655138015747},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1305786669254303},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W125553504","https://openalex.org/W1524333225","https://openalex.org/W2219249508","https://openalex.org/W2403766732","https://openalex.org/W2586956420","https://openalex.org/W2588997445","https://openalex.org/W2696967604","https://openalex.org/W2746457594","https://openalex.org/W2794506738","https://openalex.org/W2890964092","https://openalex.org/W2936774411","https://openalex.org/W2940070181","https://openalex.org/W2962866211","https://openalex.org/W2963341071","https://openalex.org/W2969985801","https://openalex.org/W2972425344","https://openalex.org/W2972961496","https://openalex.org/W2973016613","https://openalex.org/W2973062255","https://openalex.org/W2973084371","https://openalex.org/W2981087920","https://openalex.org/W2982037672","https://openalex.org/W3000589186","https://openalex.org/W3015915076","https://openalex.org/W3016143998","https://openalex.org/W3024869864","https://openalex.org/W3025686075","https://openalex.org/W3025783616","https://openalex.org/W3080158507","https://openalex.org/W3088315586","https://openalex.org/W3095851463","https://openalex.org/W3097659012","https://openalex.org/W6605243796","https://openalex.org/W6631362777","https://openalex.org/W6688816777","https://openalex.org/W6713298849","https://openalex.org/W6735429107","https://openalex.org/W6748010250","https://openalex.org/W6769723002","https://openalex.org/W6781751280"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W3141593045","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W2407001684","https://openalex.org/W3096066489","https://openalex.org/W3119184205"],"abstract_inverted_index":{"Performance":[0],"degradation":[1],"caused":[2],"by":[3,79,119],"noise":[4,88],"has":[5],"been":[6],"a":[7,18,47,120],"long-standing":[8],"challenge":[9],"for":[10,35],"speaker":[11,22,36,53,58,65,86,113],"verification.":[12],"Previous":[13],"methods":[14,30],"usually":[15],"involve":[16],"applying":[17],"denoising":[19],"transformation":[20],"to":[21,50,61,124],"embeddings":[23],"or":[24],"enhancing":[25],"input":[26],"features.":[27],"Nevertheless,":[28],"these":[29],"are":[31],"lossy":[32],"and":[33,68,87],"inefficient":[34],"embedding.":[37,54],"In":[38],"this":[39],"paper,":[40],"we":[41],"propose":[42],"context-":[43],"aware":[44],"masking":[45,75],"(CAM),":[46],"novel":[48],"method":[49],"extract":[51],"robust":[52],"CAM":[55,93,111],"enables":[56],"the":[57,64,117,125],"embedding":[59,83],"network":[60],"\"focus\"":[62],"on":[63],"of":[66,74],"interest":[67],"\"blur\"":[69],"unrelated":[70],"noise.":[71],"The":[72],"threshold":[73],"is":[76],"dynamically":[77],"controlled":[78],"an":[80,98],"auxiliary":[81],"context":[82],"that":[84,110],"captures":[85],"characteristics.":[89],"Moreover,":[90],"models":[91],"adopting":[92],"can":[94],"be":[95],"trained":[96],"in":[97,116],"end-to-end":[99],"manner":[100],"without":[101],"using":[102],"synthesized":[103],"noisy-clean":[104],"speech":[105],"pairs.":[106],"Our":[107],"results":[108],"show":[109],"improves":[112],"verification":[114],"performance":[115],"wild":[118],"large":[121],"margin,":[122],"compared":[123],"baselines.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}