{"id":"https://openalex.org/W4319587060","doi":"https://doi.org/10.1109/iscslp57327.2022.10037832","title":"A Phone-Level Speaker Embedding Extraction Framework with Multi-Gate Mixture-of-Experts Based Multi-Task Learning","display_name":"A Phone-Level Speaker Embedding Extraction Framework with Multi-Gate Mixture-of-Experts Based Multi-Task Learning","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319587060","doi":"https://doi.org/10.1109/iscslp57327.2022.10037832"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10037832","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscslp57327.2022.10037832","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5044632554","display_name":"Zhijunyi Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijunyi Yang","raw_affiliation_strings":["Wuhan University of Technology,School of Information Engineering,Wuhan,China","Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China","School of Information Engineering, Wuhan University of Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology,School of Information Engineering,Wuhan,China","institution_ids":["https://openalex.org/I196699116"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"School of Information Engineering, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067872169","display_name":"Mengjie Du","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengjie Du","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences,Shenzhen,China","University of Chinese Academy of Sciences, Beijing, China","Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036142381","display_name":"Rongfeng Su","orcid":"https://orcid.org/0000-0002-7228-5768"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210115303","display_name":"Moscow University \u00abSynergy\u00bb","ror":"https://ror.org/028mtfb17","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210115303"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN","RU"],"is_corresponding":false,"raw_author_name":"Rongfeng Su","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems","CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences","Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210115303","https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628119","display_name":"Xiaokang Liu","orcid":"https://orcid.org/0009-0009-0531-2680"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaokang Liu","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences,Shenzhen,China","University of Chinese Academy of Sciences, Beijing, China","Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062053942","display_name":"Nan Yan","orcid":"https://orcid.org/0000-0002-1613-9301"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210115303","display_name":"Moscow University \u00abSynergy\u00bb","ror":"https://ror.org/028mtfb17","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210115303"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN","RU"],"is_corresponding":false,"raw_author_name":"Nan Yan","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems","Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China","CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210115303","https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100363659","display_name":"Lan Wang","orcid":"https://orcid.org/0000-0002-9788-2577"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210115303","display_name":"Moscow University \u00abSynergy\u00bb","ror":"https://ror.org/028mtfb17","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210115303"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN","RU"],"is_corresponding":false,"raw_author_name":"Lan Wang","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems","CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences","Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210115303","https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"240","last_page":"244"},"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":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7654781341552734},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7005233764648438},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6635539531707764},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6215254068374634},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5842846035957336},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5229964256286621},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5066390633583069},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45505577325820923},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.41301560401916504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3849684000015259},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34581950306892395},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08294183015823364}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7654781341552734},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7005233764648438},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6635539531707764},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6215254068374634},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5842846035957336},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5229964256286621},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5066390633583069},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45505577325820923},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.41301560401916504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3849684000015259},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34581950306892395},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08294183015823364},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10037832","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscslp57327.2022.10037832","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7200000286102295}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1936725236","https://openalex.org/W2046056978","https://openalex.org/W2064364374","https://openalex.org/W2153682659","https://openalex.org/W2194775991","https://openalex.org/W2612434969","https://openalex.org/W2752782242","https://openalex.org/W2809290718","https://openalex.org/W2890964092","https://openalex.org/W2964247977","https://openalex.org/W2972743990","https://openalex.org/W2972938520","https://openalex.org/W2987026005","https://openalex.org/W2999547272","https://openalex.org/W3013020904","https://openalex.org/W3015648588","https://openalex.org/W3095498208","https://openalex.org/W3139024197","https://openalex.org/W3152136404","https://openalex.org/W3197848469","https://openalex.org/W3198591741","https://openalex.org/W4225634795","https://openalex.org/W4295312788","https://openalex.org/W4385245566","https://openalex.org/W6713727690","https://openalex.org/W6714259624","https://openalex.org/W6737575990"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Previous":[0],"research":[1],"has":[2],"demonstrated":[3],"that":[4],"phonetic":[5,31],"information":[6,32],"can":[7],"be":[8],"incorporated":[9],"into":[10],"speaker":[11,20,26,49,83,95,106,138,167,182,188,196],"embedding":[12,84,107,139],"models":[13],"to":[14,153],"improve":[15,162],"the":[16,19,24,36,39,45,80,118,134,137,149,155,163,166,180,191,199,204,209],"performance":[17],"of":[18,47,86,94,136,158,165,215],"recognition":[21,27],"system.":[22],"However,":[23],"current":[25],"process":[28],"base":[29],"on":[30],"is":[33,50,90,151,177],"not":[34],"in":[35,62,148],"line":[37],"with":[38,110,141],"forensic":[40],"voice":[41],"identification":[42,189],"process,":[43],"where":[44],"identity":[46],"a":[48,87,91,104,127,169,185],"determined":[51],"by":[52,57,126,208],"comparing":[53],"confident":[54,121],"phones":[55],"one":[56],"one.":[58],"This":[59],"mainly":[60],"manifests":[61],"two":[63],"aspects.":[64],"Firstly,":[65],"real-world":[66],"speech":[67],"signals":[68],"containing":[69],"unreliable":[70],"noisy":[71],"data":[72],"are":[73,124],"directly":[74],"used":[75,132,178],"as":[76,133,179],"model":[77,130],"inputs.":[78],"Secondly,":[79],"traditional":[81],"utterance-level":[82,205],"consisting":[85],"single":[88],"vector":[89,170],"coarse-grained":[92],"representation":[93],"identity.":[96],"To":[97,161],"address":[98],"these":[99],"issues,":[100],"this":[101],"paper":[102],"proposes":[103],"phone-level":[105,181,195],"extraction":[108],"framework":[109,150],"Multi-gate":[111],"Mixture-of-Experts":[112],"(MMoE)":[113],"based":[114],"multi-task":[115],"learning.":[116],"In":[117],"proposed":[119,192],"framework,":[120],"mono-phone":[122,175],"segments":[123,176],"obtained":[125],"well-trained":[128],"ASR":[129],"and":[131,144,198],"inputs":[135],"extractor":[140],"residual":[142],"structure":[143],"self-attention":[145],"mechanism.":[146],"MMoE":[147,200],"supposed":[152],"increase":[154],"modeling":[156],"sensitivity":[157],"different":[159,174],"accents.":[160],"fineness":[164],"representation,":[168],"set":[171],"generated":[172],"from":[173],"embedding.":[183],"On":[184],"large-scale":[186],"Mandarin":[187],"dataset,":[190],"system":[193,207],"using":[194],"embeddings":[197],"technique":[201],"significantly":[202],"outperformed":[203],"baseline":[206],"Top-l":[210],"average":[211],"error":[212],"rate":[213],"reduction":[214],"47.0%":[216],"relatively.":[217]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}