{"id":"https://openalex.org/W4214503194","doi":"https://doi.org/10.1109/taslp.2022.3153270","title":"Mixture Representation Learning for Deep Speaker Embedding","display_name":"Mixture Representation Learning for Deep Speaker Embedding","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4214503194","doi":"https://doi.org/10.1109/taslp.2022.3153270"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3153270","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3153270","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language 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/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, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-9241-0271","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong","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, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-8854-3760","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":1.837,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.87081759,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"30","issue":null,"first_page":"968","last_page":"978"},"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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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/mixture-model","display_name":"Mixture model","score":0.7137588262557983},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6183304190635681},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6125376224517822},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5765894651412964},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.5129101276397705},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.49455592036247253},{"id":"https://openalex.org/keywords/standard-deviation","display_name":"Standard deviation","score":0.4923778772354126},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.34269893169403076},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30315470695495605},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.18524736166000366}],"concepts":[{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7137588262557983},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6183304190635681},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6125376224517822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5765894651412964},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.5129101276397705},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.49455592036247253},{"id":"https://openalex.org/C22679943","wikidata":"https://www.wikidata.org/wiki/Q159375","display_name":"Standard deviation","level":2,"score":0.4923778772354126},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.34269893169403076},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30315470695495605},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.18524736166000366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3153270","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3153270","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2168692635","display_name":"\u7528\u4e8e\u57df\u4e0d\u53d8\u8bf4\u8bdd\u4eba\u9a8c\u8bc1\u7684\u6df1\u5c42\u5bf9\u6297\u7f51\u7edc","funder_award_id":"61971371","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":39,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1514535095","https://openalex.org/W2159786793","https://openalex.org/W2242818861","https://openalex.org/W2327501763","https://openalex.org/W2395750323","https://openalex.org/W2402146185","https://openalex.org/W2726515241","https://openalex.org/W2747165665","https://openalex.org/W2784163702","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2899771611","https://openalex.org/W2908510526","https://openalex.org/W2916104401","https://openalex.org/W2950151997","https://openalex.org/W2963371159","https://openalex.org/W2963446712","https://openalex.org/W2963507712","https://openalex.org/W2964243274","https://openalex.org/W2972433488","https://openalex.org/W2972986505","https://openalex.org/W2979476256","https://openalex.org/W3024200162","https://openalex.org/W3024869864","https://openalex.org/W3039832962","https://openalex.org/W3096127734","https://openalex.org/W3103152812","https://openalex.org/W4212863985","https://openalex.org/W4288091954","https://openalex.org/W6630875275","https://openalex.org/W6690026940","https://openalex.org/W6729448088","https://openalex.org/W6756040250","https://openalex.org/W6757817989","https://openalex.org/W6769178842","https://openalex.org/W6769196770"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W3108503355","https://openalex.org/W3090555870","https://openalex.org/W4226420367","https://openalex.org/W2962876041","https://openalex.org/W3022820045","https://openalex.org/W2801655600","https://openalex.org/W4401096132","https://openalex.org/W2899027234"],"abstract_inverted_index":{"How":[0],"to":[1,10,121,164,172],"effectively":[2],"convert":[3],"a":[4,11,17,41,47,51,78,90,123,159,199],"sequence":[5,42,62],"of":[6,40,43,108,144,157],"variable-length":[7],"acoustic":[8,61],"features":[9,151],"fixed-dimension":[12],"representation":[13],"has":[14],"always":[15],"been":[16],"research":[18],"focus":[19],"in":[20,102,210],"speaker":[21,25],"recognition.":[22],"In":[23,73],"state-of-the-art":[24],"recognition":[26],"systems,":[27],"the":[28,34,37,98,134,145,149,165,187,193,211],"conversion":[29],"is":[30,95],"implemented":[31],"by":[32,97,139,183],"concatenating":[33],"mean":[35,49,205],"and":[36,50,152,177,206],"standard":[38,53,207],"deviation":[39,54,208],"frame-level":[44,150],"features.":[45],"However,":[46],"single":[48,52,160],"are":[55,137,170,181],"limited":[56],"descriptive":[57,87],"statistics":[58,80,88],"for":[59],"an":[60,140],"even":[63],"with":[64,189],"powerful":[65,125],"feature":[66],"extractors":[67],"such":[68],"as":[69,162],"convolutional":[70],"neural":[71],"networks.":[72],"this":[74],"paper,":[75],"we":[76,114,197],"propose":[77],"novel":[79],"pooling":[81,209],"method":[82],"that":[83],"can":[84],"produce":[85,122],"more":[86,124],"through":[89],"mixture":[91,104,126,135],"representation.":[92,127],"Our":[93],"approach":[94],"inspired":[96],"expectation\u2013maximization":[99],"(EM)":[100],"algorithm":[101],"Gaussian":[103],"models":[105],"(GMMs).":[106],"Instead":[107],"using":[109,158],"traditional":[110],"GMM":[111],"style":[112],"alignment,":[113],"novelly":[115],"leverage":[116],"modern":[117],"deep":[118],"learning":[119],"tools":[120],"The":[128],"novelty":[129],"includes:":[130],"(1)":[131],"unlike":[132],"GMMs,":[133],"assignments":[136,180,185],"determined":[138],"attention":[141,166,175,195],"network":[142],"instead":[143,156],"Euclidean":[146],"distances":[147],"between":[148],"explicit":[153],"centers;":[154],"(2)":[155],"frame":[161],"input":[163],"network,":[167],"contextual":[168],"frames":[169],"included":[171],"smooth":[173],"out":[174],"transition;":[176],"(3)":[178],"soft-attention":[179],"replaced":[182],"hard-attention":[184],"via":[186],"Gumbel-Softmax":[188],"straight-through":[190],"estimators.":[191],"With":[192],"proposed":[194],"mechanism,":[196],"obtained":[198],"13.7%":[200],"relative":[201],"improvement":[202],"over":[203],"vanilla":[204],"VOiCES19-eval":[212],"set.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}