{"id":"https://openalex.org/W3012043827","doi":"https://doi.org/10.1109/taslp.2020.2980372","title":"Online Speaker Adaptation Using Memory-Aware Networks for Speech Recognition","display_name":"Online Speaker Adaptation Using Memory-Aware Networks for Speech Recognition","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3012043827","doi":"https://doi.org/10.1109/taslp.2020.2980372","mag":"3012043827"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.2980372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2980372","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/A5101924451","display_name":"Jia Pan","orcid":"https://orcid.org/0000-0002-7073-1744"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jia Pan","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011133553","display_name":"Genshun Wan","orcid":"https://orcid.org/0000-0002-5813-9430"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Genshun Wan","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065761465","display_name":"Zhongfu Ye","orcid":"https://orcid.org/0000-0002-3207-2258"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongfu Ye","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101924451"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.5302,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.71585585,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"28","issue":null,"first_page":"1025","last_page":"1037"},"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":0.9994999766349792,"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":0.9947999715805054,"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":0.802506685256958},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.641167402267456},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5159514546394348},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.49492043256759644},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.4816361963748932},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47626993060112},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4685075581073761},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.46581247448921204},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.4588518738746643},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4487626552581787},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.42781734466552734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34209296107292175},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17477256059646606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.802506685256958},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.641167402267456},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5159514546394348},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.49492043256759644},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.4816361963748932},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47626993060112},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4685075581073761},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.46581247448921204},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.4588518738746643},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4487626552581787},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.42781734466552734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34209296107292175},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17477256059646606},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2020.2980372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2980372","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":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G573022218","display_name":null,"funder_award_id":"U1613211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8173470123","display_name":null,"funder_award_id":"61671422","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":84,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W854541894","https://openalex.org/W1513820424","https://openalex.org/W1513862252","https://openalex.org/W1567690964","https://openalex.org/W1586176709","https://openalex.org/W1686810756","https://openalex.org/W1770758908","https://openalex.org/W1882958252","https://openalex.org/W1902237438","https://openalex.org/W1987238397","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2001619934","https://openalex.org/W2010362084","https://openalex.org/W2046056978","https://openalex.org/W2048526313","https://openalex.org/W2056738732","https://openalex.org/W2079623482","https://openalex.org/W2080005694","https://openalex.org/W2087006792","https://openalex.org/W2090320273","https://openalex.org/W2094147890","https://openalex.org/W2096733369","https://openalex.org/W2112021726","https://openalex.org/W2125234026","https://openalex.org/W2127218421","https://openalex.org/W2133564696","https://openalex.org/W2147768505","https://openalex.org/W2150769028","https://openalex.org/W2155273149","https://openalex.org/W2155893237","https://openalex.org/W2160306971","https://openalex.org/W2166637769","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2198724430","https://openalex.org/W2293634267","https://openalex.org/W2296483664","https://openalex.org/W2400607496","https://openalex.org/W2403307129","https://openalex.org/W2407793339","https://openalex.org/W2508162385","https://openalex.org/W2511131004","https://openalex.org/W2559260703","https://openalex.org/W2641129314","https://openalex.org/W2734498959","https://openalex.org/W2759604924","https://openalex.org/W2760103357","https://openalex.org/W2769025471","https://openalex.org/W2795867901","https://openalex.org/W2796339975","https://openalex.org/W2799674897","https://openalex.org/W2889048668","https://openalex.org/W2891286407","https://openalex.org/W2920796740","https://openalex.org/W2939164678","https://openalex.org/W2939173691","https://openalex.org/W2953127297","https://openalex.org/W2963266252","https://openalex.org/W2963381607","https://openalex.org/W2963403868","https://openalex.org/W2963826681","https://openalex.org/W2964308564","https://openalex.org/W3099206234","https://openalex.org/W4385245566","https://openalex.org/W6603403951","https://openalex.org/W6623517193","https://openalex.org/W6630673164","https://openalex.org/W6637373629","https://openalex.org/W6639480849","https://openalex.org/W6678914141","https://openalex.org/W6679434410","https://openalex.org/W6696934422","https://openalex.org/W6697003656","https://openalex.org/W6713701104","https://openalex.org/W6713823255","https://openalex.org/W6725448924","https://openalex.org/W6735593169","https://openalex.org/W6739901393","https://openalex.org/W6740674931","https://openalex.org/W6743152796","https://openalex.org/W6745924425","https://openalex.org/W6754473786"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W4406496871","https://openalex.org/W1521049138","https://openalex.org/W2023466863"],"abstract_inverted_index":{"In":[0,27],"our":[1,6,160,189],"previous":[2],"work,":[3],"we":[4,30,134],"introduced":[5],"attention-based":[7],"speaker":[8,20,86,124,165,228],"adaptation":[9,21,166,172,229],"method,":[10],"which":[11,42,144],"has":[12],"been":[13],"proved":[14],"to":[15,67,77,91,111,203,222],"be":[16],"an":[17],"efficient":[18],"online":[19,164],"method":[22,38,104,161,190],"for":[23],"real-time":[24],"speech":[25],"recognition.":[26],"this":[28,37],"paper,":[29],"present":[31],"a":[32,62,136,177,192],"more":[33],"complete":[34],"framework":[35],"of":[36,44,81,95,120,139,198,205,224],"named":[39],"memory-aware":[40],"networks,":[41],"consists":[43],"the":[45,48,51,55,69,72,82,93,96,132,153,186,206,210,214,225],"main":[46,73],"network,":[47],"memory":[49,70,140],"module,":[50],"attention":[52,97],"module":[53],"and":[54,61,115,155,174,200,213,218],"connection":[56],"module.":[57,98],"A":[58],"gate":[59],"mechanism":[60],"multiple-connections":[63],"strategy":[64],"are":[65],"presented":[66],"connect":[68],"with":[71,108,169,175],"network":[74],"in":[75,181],"order":[76],"take":[78],"full":[79],"advantage":[80],"memory.":[83],"An":[84],"auxiliary":[85],"classification":[87],"task":[88,212],"is":[89,105],"provided":[90],"improve":[92],"accuracy":[94],"The":[99],"fixed-size":[100],"ordinally":[101],"forgetting":[102],"encoding":[103],"used":[106],"together":[107],"average":[109],"pooling":[110],"gather":[112],"both":[113,152],"short-term":[114],"long-term":[116],"information.":[117],"Furthermore,":[118],"instead":[119],"only":[121,176],"using":[122],"traditional":[123,226],"embeddings":[125],"such":[126],"as":[127,131],"i-vectors":[128],"or":[129],"d-vectors":[130],"memory,":[133],"design":[135],"new":[137],"form":[138],"called":[141],"residual":[142],"vectors,":[143],"can":[145,162],"represent":[146],"different":[147],"pronunciation":[148],"habits.":[149],"Experiments":[150],"on":[151,209],"Switchboard":[154,211],"AISHELL-2":[156,215],"tasks":[157],"show":[158],"that":[159,204,223],"perform":[163],"very":[167],"well":[168],"no":[170],"additional":[171],"data":[173],"relative":[178,193],"3%":[179],"increase":[180],"decoding":[182],"computation":[183],"complexity.":[184],"Under":[185],"cross-entropy":[187],"criterion,":[188],"achieves":[191],"word":[194],"error":[195],"rate":[196],"reduction":[197],"9.4%":[199],"8.3%":[201],"compared":[202,221],"speaker-independent":[207],"model":[208],"task,":[216],"respectively,":[217],"approximately":[219],"7.0%":[220],"d-vector-based":[227],"method.":[230]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}