{"id":"https://openalex.org/W4224924624","doi":"https://doi.org/10.1109/icassp43922.2022.9747778","title":"Disentangled Speaker Embedding for Robust Speaker Verification","display_name":"Disentangled Speaker Embedding for Robust Speaker Verification","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224924624","doi":"https://doi.org/10.1109/icassp43922.2022.9747778"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747778","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5008845262","display_name":"Yi Lu","orcid":"https://orcid.org/0000-0002-4803-9305"},"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":"Lu Yi","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electronic and Information Engineering,Hong Kong SAR","Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electronic and Information Engineering,Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","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,Department of Electronic and Information Engineering,Hong Kong SAR","Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electronic and Information Engineering,Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5008845262"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":0.7323,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.69958128,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7662","last_page":"7666"},"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":0.9976999759674072,"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":0.995199978351593,"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/infomax","display_name":"Infomax","score":0.8824801445007324},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.790177583694458},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6978327631950378},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.677206814289093},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.63788241147995},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.6088384389877319},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5651410222053528},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5326478481292725},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.529544472694397},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.50815749168396},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.49445486068725586},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4663284122943878},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.4620605707168579},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4335031807422638},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4158076047897339},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09691685438156128},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.08766552805900574},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.08699563145637512}],"concepts":[{"id":"https://openalex.org/C153402090","wikidata":"https://www.wikidata.org/wiki/Q6030480","display_name":"Infomax","level":4,"score":0.8824801445007324},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.790177583694458},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6978327631950378},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.677206814289093},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.63788241147995},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.6088384389877319},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5651410222053528},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5326478481292725},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.529544472694397},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.50815749168396},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.49445486068725586},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4663284122943878},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4620605707168579},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4335031807422638},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4158076047897339},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09691685438156128},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.08766552805900574},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.08699563145637512},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747778","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7400000095367432}],"awards":[],"funders":[{"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":33,"referenced_works":["https://openalex.org/W1589137271","https://openalex.org/W2046015436","https://openalex.org/W2096733369","https://openalex.org/W2150769028","https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2747165665","https://openalex.org/W2794506738","https://openalex.org/W2801581493","https://openalex.org/W2803832867","https://openalex.org/W2808631503","https://openalex.org/W2887997457","https://openalex.org/W2888473984","https://openalex.org/W2890964092","https://openalex.org/W2912280829","https://openalex.org/W2953127297","https://openalex.org/W2963040451","https://openalex.org/W2963450999","https://openalex.org/W2968917279","https://openalex.org/W2972697221","https://openalex.org/W2973099347","https://openalex.org/W3024855809","https://openalex.org/W3097256596","https://openalex.org/W3163829335","https://openalex.org/W3198310187","https://openalex.org/W6635152626","https://openalex.org/W6688816777","https://openalex.org/W6725448924","https://openalex.org/W6752051073","https://openalex.org/W6754278344","https://openalex.org/W6758833332","https://openalex.org/W6767164110"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W3141593045","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Entanglement":[0],"of":[1,86],"speaker":[2,14,42,113],"features":[3,6,39,43,64],"and":[4,31,40,65,111],"redundant":[5],"may":[7],"lead":[8],"to":[9,35,57,89],"poor":[10],"performance":[11],"when":[12],"evaluating":[13],"verification":[15],"systems":[16],"on":[17,45,83,97],"an":[18,27],"unseen":[19],"domain.":[20],"To":[21],"address":[22],"this":[23],"issue,":[24],"we":[25,77],"propose":[26,78],"InfoMax":[28],"domain":[29,46],"separation":[30],"adaptation":[32,47],"network":[33],"(InfoMax\u2013DSAN)":[34],"disentangle":[36],"the":[37,59,84,91],"domain-specific":[38],"domain-invariant":[41],"based":[44,82],"techniques.":[48],"A":[49],"frame-based":[50],"mutual":[51,60],"information":[52,61],"neural":[53],"estimator":[54],"is":[55],"proposed":[56,104],"maximize":[58],"between":[62],"frame-level":[63],"input":[66],"acoustic":[67],"features,":[68],"which":[69],"can":[70,106],"help":[71,107],"retain":[72],"more":[73,109],"useful":[74],"information.":[75],"Furthermore,":[76],"adopting":[79],"triplet":[80],"loss":[81],"idea":[85],"self-supervised":[87],"learning":[88],"overcome":[90],"label":[92],"mismatch":[93],"problem.":[94],"Experimental":[95],"results":[96],"VOiCES":[98],"Challenge":[99],"2019":[100],"demonstrate":[101],"that":[102],"our":[103],"method":[105],"learn":[108],"discriminative":[110],"robust":[112],"embeddings.":[114]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}