{"id":"https://openalex.org/W2972621414","doi":"https://doi.org/10.21437/interspeech.2019-3135","title":"Speaker Adaptation for Attention-Based End-to-End Speech Recognition","display_name":"Speaker Adaptation for Attention-Based End-to-End Speech Recognition","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972621414","doi":"https://doi.org/10.21437/interspeech.2019-3135","mag":"2972621414"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-3135","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.03762","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101749753","display_name":"Zhong Meng","orcid":"https://orcid.org/0000-0001-7814-5929"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhong Meng","raw_affiliation_strings":["(Microsoft)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034136587","display_name":"Yashesh Gaur","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yashesh Gaur","raw_affiliation_strings":["(Microsoft)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["(Microsoft)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"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/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["(Microsoft)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"241","last_page":"245"},"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":0.9955999851226807,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8485633134841919},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7137575149536133},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6963278651237488},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5879564881324768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24201053380966187},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14653632044792175},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.0621623694896698}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8485633134841919},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7137575149536133},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6963278651237488},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5879564881324768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24201053380966187},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14653632044792175},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0621623694896698}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2019-3135","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1911.03762","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.03762","pdf_url":"https://arxiv.org/pdf/1911.03762","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1911.03762","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.03762","pdf_url":"https://arxiv.org/pdf/1911.03762","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1828163288","https://openalex.org/W1882958252","https://openalex.org/W1899458394","https://openalex.org/W1924770834","https://openalex.org/W1965555277","https://openalex.org/W1989549063","https://openalex.org/W2010362084","https://openalex.org/W2099471712","https://openalex.org/W2102113734","https://openalex.org/W2112021726","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2160306971","https://openalex.org/W2239847623","https://openalex.org/W2294543795","https://openalex.org/W2327501763","https://openalex.org/W2394882406","https://openalex.org/W2407793339","https://openalex.org/W2508162385","https://openalex.org/W2510867321","https://openalex.org/W2511423218","https://openalex.org/W2584667682","https://openalex.org/W2587088898","https://openalex.org/W2636483419","https://openalex.org/W2769025471","https://openalex.org/W2795867901","https://openalex.org/W2796339975","https://openalex.org/W2888858245","https://openalex.org/W2889500840","https://openalex.org/W2890351244","https://openalex.org/W2891980359","https://openalex.org/W2899771611","https://openalex.org/W2936252403","https://openalex.org/W2937328535","https://openalex.org/W2938486422","https://openalex.org/W2939164678","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963341071","https://openalex.org/W2963523217","https://openalex.org/W2963826681","https://openalex.org/W2963970535","https://openalex.org/W2964182776","https://openalex.org/W2964199361","https://openalex.org/W2964308564","https://openalex.org/W3112742522","https://openalex.org/W4320013936","https://openalex.org/W4394666973"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W4404782863"],"abstract_inverted_index":{"We":[0],"propose":[1],"three":[2,159],"regularization-based":[3],"speaker":[4,77],"adaptation":[5,17,64,78],"approaches":[6],"to":[7,47,50,62,83,118,144,171],"adapt":[8],"the":[9,37,53,63,69,85,89,93,101,108,121,146,166],"attention-based":[10],"encoder-decoder":[11],"(AED)":[12],"model":[13,56],"with":[14],"very":[15],"limited":[16],"data":[18,187],"from":[19,184],"target":[20,147],"speakers":[21],"for":[22,68,188],"end-to-end":[23],"automatic":[24],"speech":[25],"recognition.":[26],"The":[27,104],"first":[28],"method":[29,80],"is":[30,45,81,107,116],"Kullback-Leibler":[31],"divergence":[32],"(KLD)":[33],"regularization,":[34,74],"in":[35,72,111,164],"which":[36,112],"output":[38,130,142],"distribution":[39,87],"of":[40,52,88,96,124,129,136,141],"a":[41,59,126,138,152],"speaker-dependent":[42],"(SD)":[43],"AED":[44,91,115,167,182],"forced":[46],"be":[48],"close":[49],"that":[51],"speaker-independent":[54],"(SI)":[55],"by":[57],"adding":[58],"KLD":[60,73],"regularization":[61],"criterion.":[65],"To":[66],"compensate":[67],"asymmetric":[70],"deficiency":[71],"an":[75,97,113,133,180],"adversarial":[76,94],"(ASA)":[79],"proposed":[82],"regularize":[84],"deep-feature":[86],"SD":[90,102,114],"through":[92],"learning":[95],"auxiliary":[98,134],"discriminator":[99],"and":[100,132,173,190],"AED.":[103],"third":[105],"approach":[106],"multi-task":[109],"learning,":[110],"trained":[117,183],"jointly":[119],"perform":[120],"primary":[122],"task":[123,135],"predicting":[125,137],"large":[127],"number":[128,140],"units":[131,143],"small":[139],"alleviate":[145],"sparsity":[148],"issue.":[149],"Evaluated":[150],"on":[151],"Microsoft":[153],"short":[154],"message":[155],"dictation":[156],"task,":[157],"all":[158],"methods":[160],"are":[161],"highly":[162],"effective":[163],"adapting":[165],"model,":[168],"achieving":[169],"up":[170],"12.2%":[172],"3.0%":[174],"word":[175],"error":[176],"rate":[177],"improvement":[178],"over":[179],"SI":[181],"3400":[185],"hours":[186],"supervised":[189],"unsupervised":[191],"adaptation,":[192],"respectively.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}