{"id":"https://openalex.org/W2400607496","doi":"https://doi.org/10.1109/icassp.2016.7472633","title":"Investigations on speaker adaptation of LSTM RNN models for speech recognition","display_name":"Investigations on speaker adaptation of LSTM RNN models for speech recognition","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2400607496","doi":"https://doi.org/10.1109/icassp.2016.7472633","mag":"2400607496"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5004148430","display_name":"Chaojun Liu","orcid":"https://orcid.org/0000-0002-4676-3981"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaojun Liu","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339989","display_name":"Yongqiang Wang","orcid":"https://orcid.org/0000-0002-8600-0276"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongqiang Wang","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047826067","display_name":"Kshitiz Kumar","orcid":"https://orcid.org/0000-0003-2728-2493"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kshitiz Kumar","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":4.0771,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.95723728,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.996999979019165,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9940000176429749,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8049968481063843},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7679022550582886},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7209486365318298},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6067073345184326},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5658001899719238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5427073240280151},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5222252607345581},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.502671480178833},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4640471339225769},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.45135697722435},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44841375946998596},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4370483458042145},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4313446283340454},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3427122235298157},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3384120762348175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8049968481063843},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7679022550582886},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7209486365318298},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6067073345184326},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5658001899719238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5427073240280151},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5222252607345581},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.502671480178833},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4640471339225769},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.45135697722435},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44841375946998596},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4370483458042145},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4313446283340454},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3427122235298157},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3384120762348175},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W567546468","https://openalex.org/W1513820424","https://openalex.org/W1567690964","https://openalex.org/W1770758908","https://openalex.org/W1985371235","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2005708641","https://openalex.org/W2010362084","https://openalex.org/W2056738732","https://openalex.org/W2056825827","https://openalex.org/W2064675550","https://openalex.org/W2079623482","https://openalex.org/W2087006792","https://openalex.org/W2094147890","https://openalex.org/W2107878631","https://openalex.org/W2119615570","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2157711090","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2181607856","https://openalex.org/W2184045248","https://openalex.org/W2293009711","https://openalex.org/W2293634267","https://openalex.org/W2295119550","https://openalex.org/W2403307129","https://openalex.org/W2403524927","https://openalex.org/W2403797310","https://openalex.org/W2408125366","https://openalex.org/W6603403951","https://openalex.org/W6615969787","https://openalex.org/W6686045668","https://openalex.org/W6696934422","https://openalex.org/W6696982659","https://openalex.org/W6697090674","https://openalex.org/W6713292810","https://openalex.org/W6713297655","https://openalex.org/W6713701104","https://openalex.org/W6714155552"],"related_works":["https://openalex.org/W2121652828","https://openalex.org/W3033124456","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W642007152","https://openalex.org/W2122233706","https://openalex.org/W2105439218","https://openalex.org/W3143423642","https://openalex.org/W2131711534","https://openalex.org/W2341426843"],"abstract_inverted_index":{"Recently":[0],"Long":[1],"Short-Term":[2],"Memory":[3],"(LSTM)":[4],"Recurrent":[5],"Neural":[6],"Networks":[7],"(RNN)":[8],"acoustic":[9],"models":[10,20,62],"have":[11,33],"demonstrated":[12],"superior":[13],"performance":[14],"over":[15,134],"deep":[16],"neural":[17],"networks":[18],"(DNN)":[19],"in":[21],"speech":[22,64,102],"recognition":[23,103],"and":[24,77,87,95,127],"many":[25],"other":[26],"tasks.":[27],"Although":[28],"a":[29,92,99,135],"lot":[30],"of":[31,57,60,109],"work":[32],"been":[34,43],"reported":[35],"on":[36,45,123,130],"DNN":[37],"model":[38,47,112],"adaptation,":[39],"very":[40],"little":[41],"has":[42],"done":[44],"LSTM":[46,111,137],"adaptation.":[48],"In":[49,98],"this":[50],"paper":[51],"we":[52,119],"present":[53],"our":[54],"extensive":[55],"studies":[56],"speaker":[58],"adaptation":[59,69,86],"LSTM-RNN":[61],"for":[63],"recognition.":[65],"We":[66,90],"investigated":[67],"different":[68],"methods":[70],"combined":[71],"with":[72],"KL-divergence":[73],"based":[74],"regularization,":[75],"where":[76],"which":[78],"network":[79],"component":[80],"to":[81],"adapt,":[82],"supervised":[83],"versus":[84],"unsupervised":[85],"asymptotic":[88],"analysis.":[89],"made":[91],"few":[93],"distinct":[94],"important":[96],"observations.":[97],"large":[100],"vocabulary":[101],"task,":[104],"by":[105],"adapting":[106],"only":[107],"2.5%":[108],"the":[110,124,131],"parameters":[113],"using":[114],"50":[115],"utterances":[116],"per":[117],"speaker,":[118],"obtained":[120],"12.6%":[121],"WERR":[122,129],"dev":[125],"set":[126,133],"9.1%":[128],"evaluation":[132],"strong":[136],"baseline":[138],"model.":[139]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}