{"id":"https://openalex.org/W3015639015","doi":"https://doi.org/10.1109/icassp40776.2020.9053191","title":"Adaptation of RNN Transducer with Text-To-Speech Technology for Keyword Spotting","display_name":"Adaptation of RNN Transducer with Text-To-Speech Technology for Keyword Spotting","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015639015","doi":"https://doi.org/10.1109/icassp40776.2020.9053191","mag":"3015639015"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5020793872","display_name":"Eva Sharma","orcid":"https://orcid.org/0000-0002-1328-508X"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Eva Sharma","raw_affiliation_strings":["Khoury College of Computer Sciences, Northeastern University, Boston"],"affiliations":[{"raw_affiliation_string":"Khoury College of Computer Sciences, Northeastern University, Boston","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008578397","display_name":"Guoli Ye","orcid":null},"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":"Guoli Ye","raw_affiliation_strings":["Speech and Language Group, Microsoft"],"affiliations":[{"raw_affiliation_string":"Speech and Language Group, Microsoft","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055564488","display_name":"Wenning Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenning Wei","raw_affiliation_strings":["Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101987526","display_name":"Rui Zhao","orcid":"https://orcid.org/0000-0002-9699-9984"},"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":"Rui Zhao","raw_affiliation_strings":["Speech and Language Group, Microsoft"],"affiliations":[{"raw_affiliation_string":"Speech and Language Group, Microsoft","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080127413","display_name":"Yao Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Tian","raw_affiliation_strings":["Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101674460","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3101-7011"},"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":"Jian Wu","raw_affiliation_strings":["Speech and Language Group, Microsoft"],"affiliations":[{"raw_affiliation_string":"Speech and Language Group, Microsoft","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061724331","display_name":"Lei He","orcid":"https://orcid.org/0000-0003-3028-6305"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei He","raw_affiliation_strings":["Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062230378","display_name":"Ed Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ed Lin","raw_affiliation_strings":["Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077401426","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0001-8786-3391"},"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":["Speech and Language Group, Microsoft"],"affiliations":[{"raw_affiliation_string":"Speech and Language Group, Microsoft","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5020793872"],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":1.9315,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.88758006,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7484","last_page":"7488"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9987000226974487,"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":0.9973999857902527,"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/keyword-spotting","display_name":"Keyword spotting","score":0.9739944338798523},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8762956261634827},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.797092616558075},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6322125196456909},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.5632238388061523},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5422601699829102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4756445586681366},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.4347985088825226},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3511289656162262}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9739944338798523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8762956261634827},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.797092616558075},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6322125196456909},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.5632238388061523},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5422601699829102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4756445586681366},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.4347985088825226},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3511289656162262},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1989549063","https://openalex.org/W2294543795","https://openalex.org/W2327501763","https://openalex.org/W2510945575","https://openalex.org/W2545177271","https://openalex.org/W2558258029","https://openalex.org/W2578392894","https://openalex.org/W2697044473","https://openalex.org/W2889385306","https://openalex.org/W2889423969","https://openalex.org/W2903853691","https://openalex.org/W2904459034","https://openalex.org/W2962707338","https://openalex.org/W2962760690","https://openalex.org/W2963523217","https://openalex.org/W2963970535","https://openalex.org/W2972880214","https://openalex.org/W2972889948","https://openalex.org/W2972895620","https://openalex.org/W2973051376","https://openalex.org/W3007227084","https://openalex.org/W4294621971","https://openalex.org/W6629717138","https://openalex.org/W6696912008","https://openalex.org/W6729959887","https://openalex.org/W6744661987","https://openalex.org/W6757322325","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W9939214","https://openalex.org/W14635080","https://openalex.org/W4781179","https://openalex.org/W1208717","https://openalex.org/W1845554","https://openalex.org/W10064791","https://openalex.org/W8493306","https://openalex.org/W12861721","https://openalex.org/W8315361","https://openalex.org/W1750090"],"abstract_inverted_index":{"With":[0,45],"the":[1,10,21,31,50,101,112,116,122,158],"advent":[2],"of":[3,12,33,139,157,169],"recurrent":[4],"neural":[5],"network":[6],"transducer":[7],"(RNN-T)":[8],"model,":[9,82,95],"performance":[11,41,52,114,123,151],"keyword":[13,34],"spotting":[14],"(KWS)":[15],"systems":[16],"has":[17],"greatly":[18],"improved.":[19],"However,":[20],"KWS":[22,51,81],"systems,":[23],"employed":[24],"for":[25,38,53,74,115],"wake-word":[26],"detection,":[27],"still":[28],"rely":[29],"on":[30,42,86,135],"availability":[32],"specific":[35,155],"training":[36,72,127],"data":[37,73,140,144],"achieving":[39],"reasonable":[40],"each":[43],"keyword.":[44],"a":[46,93,108],"goal":[47],"to":[48,58,69,130],"improve":[49],"these":[54],"keywords":[55],"without":[56],"having":[57],"collect":[59],"additional":[60,148],"natural":[61,89,131],"speech":[62,90,132],"data,":[63,128,133],"we":[64,96,119],"explore":[65],"Text-To-Speech":[66],"(TTS)":[67],"technology":[68],"synthetically":[70],"generate":[71],"such":[75],"keywords.":[76],"Employing":[77],"an":[78],"RNN-T":[79,159,170],"based":[80],"already":[83],"well":[84],"trained":[85],"large":[87],"keyword-independent":[88],"dataset,":[91],"as":[92],"seed":[94],"run":[97],"adaptation":[98],"experiments":[99],"using":[100],"generated":[102],"keyword-specific":[103],"TTS":[104],"data.":[105],"Besides":[106],"observing":[107],"considerable":[109],"improvement":[110,124,149],"in":[111,150],"overall":[113],"low-resource":[117],"keywords,":[118],"find":[120],"that":[121],"with":[125],"TTS-generated":[126],"similar":[129],"depends":[134],"speaker":[136,142],"diversity,":[137],"amount":[138],"per":[141],"and":[143,161],"simulation.":[145],"We":[146],"get":[147],"by":[152],"selectively":[153],"adapting":[154],"parts":[156],"model":[160],"gain":[162],"key":[163],"insights":[164],"into":[165],"different":[166],"architectural":[167],"constructs":[168],"model.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":8}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}