{"id":"https://openalex.org/W2972799770","doi":"https://doi.org/10.21437/interspeech.2019-2719","title":"Listen, Attend, Spell and Adapt: Speaker Adapted Sequence-to-Sequence ASR","display_name":"Listen, Attend, Spell and Adapt: Speaker Adapted Sequence-to-Sequence ASR","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972799770","doi":"https://doi.org/10.21437/interspeech.2019-2719","mag":"2972799770"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2719","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2719","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":"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/A5016747567","display_name":"Felix Weninger","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Felix Weninger","raw_affiliation_strings":["Nuance Communications, Inc., 1 Burlington, MA, USA,"],"affiliations":[{"raw_affiliation_string":"Nuance Communications, Inc., 1 Burlington, MA, USA,","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019869698","display_name":"Jes\u00fas Andr\u00e9s-Ferrer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jes\u00fas Andr\u00e9s-Ferrer","raw_affiliation_strings":["Valencia, Spain"],"affiliations":[{"raw_affiliation_string":"Valencia, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461522","display_name":"Xinwei Li","orcid":"https://orcid.org/0009-0005-9677-0011"},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinwei Li","raw_affiliation_strings":["Nuance Communications, Inc., 1 Burlington, MA, USA,"],"affiliations":[{"raw_affiliation_string":"Nuance Communications, Inc., 1 Burlington, MA, USA,","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109588257","display_name":"Puming Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Puming Zhan","raw_affiliation_strings":["Nuance Communications, Inc., 1 Burlington, MA, USA,"],"affiliations":[{"raw_affiliation_string":"Nuance Communications, Inc., 1 Burlington, MA, USA,","institution_ids":["https://openalex.org/I4210125787"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5016747567"],"corresponding_institution_ids":["https://openalex.org/I4210125787"],"apc_list":null,"apc_paid":null,"fwci":2.5203,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.91936581,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3805","last_page":"3809"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9958999752998352,"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":0.9944999814033508,"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":0.7569465041160583},{"id":"https://openalex.org/keywords/dictation","display_name":"Dictation","score":0.7089880704879761},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6779506206512451},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6570241451263428},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6333679556846619},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.5335921049118042},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5151742696762085},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.47047048807144165},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4687402844429016},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08629322052001953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7569465041160583},{"id":"https://openalex.org/C2779077324","wikidata":"https://www.wikidata.org/wiki/Q1087138","display_name":"Dictation","level":2,"score":0.7089880704879761},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6779506206512451},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6570241451263428},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6333679556846619},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5335921049118042},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5151742696762085},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.47047048807144165},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4687402844429016},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08629322052001953},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-2719","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2719","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6899999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1513862252","https://openalex.org/W1591801644","https://openalex.org/W1828163288","https://openalex.org/W1989549063","https://openalex.org/W2079623482","https://openalex.org/W2080005694","https://openalex.org/W2095705004","https://openalex.org/W2120861206","https://openalex.org/W2133564696","https://openalex.org/W2143612262","https://openalex.org/W2162042984","https://openalex.org/W2183341477","https://openalex.org/W2327501763","https://openalex.org/W2398187210","https://openalex.org/W2398776621","https://openalex.org/W2403195671","https://openalex.org/W2403797310","https://openalex.org/W2577366047","https://openalex.org/W2613904329","https://openalex.org/W2886319145","https://openalex.org/W2889152503","https://openalex.org/W2889181648","https://openalex.org/W2889374926","https://openalex.org/W2890964092","https://openalex.org/W2891980359","https://openalex.org/W2962940707","https://openalex.org/W2963240019","https://openalex.org/W2963362078","https://openalex.org/W2963747784","https://openalex.org/W2963827914"],"related_works":["https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2156060302","https://openalex.org/W2050138804","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W26527944","https://openalex.org/W2523799048","https://openalex.org/W2155620340"],"abstract_inverted_index":{"Sequence-to-sequence":[0],"(seq2seq)":[1],"based":[2,77,154],"ASR":[3,25,63],"systems":[4,31],"have":[5],"shown":[6],"state-of-the-art":[7,106],"performances":[8],"while":[9],"having":[10],"clear":[11],"advantages":[12],"in":[13,35,130,177],"terms":[14],"of":[15,57,61,89,101,119,139,148,180],"simplicity.However,":[16],"comparisons":[17],"are":[18,32,96],"mostly":[19],"done":[20],"on":[21,98,155],"speaker":[22,28,41,49,171],"independent":[23],"(SI)":[24],"systems,":[26],"though":[27],"adapted":[29,172],"conventional":[30,62,132],"commonly":[33],"used":[34],"practice":[36],"for":[37,79,166],"improving":[38],"robustness":[39],"to":[40,51,86],"and":[42,104,160],"environment":[43],"variations.In":[44],"this":[45],"paper,":[46],"we":[47,65,151],"apply":[48],"adaptation":[50,78,90,118,129,149,153],"seq2seq":[52,80,121,141,173,182],"models":[53,95],"with":[54,116,145,169],"the":[55,59,120,131,137,140,146,156,162,170,181],"goal":[56],"matching":[58],"performance":[60],"adaptation.Specifically,":[64],"investigate":[66],"Kullback-Leibler":[67],"divergence":[68],"(KLD)":[69],"as":[70,72],"well":[71],"Linear":[73],"Hidden":[74],"Network":[75],"(LHN)":[76],"ASR,":[81],"using":[82],"different":[83],"amounts":[84,100],"(up":[85],"20":[87],"hours)":[88],"data":[91,103],"per":[92],"speaker.Our":[93],"SI":[94],"trained":[97],"large":[99],"dictation":[102],"achieve":[105],"results.We":[107],"obtained":[108],"25%":[109],"relative":[110],"word":[111],"error":[112],"rate":[113],"(WER)":[114],"improvement":[115],"KLD":[117],"model":[122,128,142,164],"vs.":[123],"18.7%":[124],"gain":[125],"from":[126],"acoustic":[127],"system.We":[133],"also":[134],"show":[135],"that":[136],"WER":[138,158],"decreases":[143],"log-linearly":[144],"amount":[147],"data.Finally,":[150],"analyze":[152],"minimum":[157],"criterion":[159],"adapting":[161],"language":[163],"(LM)":[165],"score":[167],"fusion":[168],"model,":[174],"which":[175],"result":[176],"further":[178],"improvements":[179],"system":[183],"performance.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}