{"id":"https://openalex.org/W3080248383","doi":"https://doi.org/10.21437/interspeech.2020-1290","title":"Rapid RNN-T Adaptation Using Personalized Speech Synthesis and Neural Language Generator","display_name":"Rapid RNN-T Adaptation Using Personalized Speech Synthesis and Neural Language Generator","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3080248383","doi":"https://doi.org/10.21437/interspeech.2020-1290","mag":"3080248383"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1290","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5101550628","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0002-8239-7229"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061724331","display_name":"Lei He","orcid":"https://orcid.org/0000-0003-3028-6305"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055564488","display_name":"Wenning Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenning Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068671901","display_name":"William A. Gale","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"William Gale","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5077401426","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0001-8786-3391"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.265,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.83772918,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1256","last_page":"1260"},"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":0.9969000220298767,"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":0.9876999855041504,"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":0.7858361601829529},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7214927673339844},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6367263793945312},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6218889951705933},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5653291940689087},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5290255546569824},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.4246790111064911},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4167514443397522},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40328386425971985},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.23825496435165405},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.13293185830116272}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7858361601829529},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7214927673339844},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6367263793945312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6218889951705933},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5653291940689087},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5290255546569824},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.4246790111064911},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4167514443397522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40328386425971985},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.23825496435165405},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.13293185830116272},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1290","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2056738732","https://openalex.org/W2079623482","https://openalex.org/W2127141656","https://openalex.org/W2239847623","https://openalex.org/W2276408190","https://openalex.org/W2293829681","https://openalex.org/W2327501763","https://openalex.org/W2402268235","https://openalex.org/W2508162385","https://openalex.org/W2526425061","https://openalex.org/W2886319145","https://openalex.org/W2889012072","https://openalex.org/W2962760690","https://openalex.org/W2962826786","https://openalex.org/W2963403868","https://openalex.org/W2963414781","https://openalex.org/W2964243274","https://openalex.org/W2972895620","https://openalex.org/W3006752097","https://openalex.org/W3007227084","https://openalex.org/W3011339933","https://openalex.org/W3015216127","https://openalex.org/W3015686596","https://openalex.org/W3016008406","https://openalex.org/W3094667432"],"related_works":["https://openalex.org/W2374250903","https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W3017902212","https://openalex.org/W2964335273","https://openalex.org/W2982145560"],"abstract_inverted_index":{"Rapid":[0],"unsupervised":[1],"speaker":[2,43,70,102],"adaptation":[3,44,71,103],"in":[4,18,50,72,105],"an":[5,73],"E2E":[6],"system":[7,53],"posits":[8],"us":[9],"new":[10],"challenges":[11],"due":[12],"to":[13,20,66,100,135],"its":[14,21],"end-to-end":[15],"unified":[16],"structure":[17],"addition":[19],"intrinsic":[22],"difficulty":[23],"of":[24,164],"data":[25,173],"sparsity":[26],"and":[27,45,87,92,176],"imperfect":[28],"label":[29],"[1].":[30],"Previously":[31],"we":[32,58],"proposed":[33,79,98],"utilizing":[34],"the":[35,60,85,90,97,113,131,136,147,162,165,179],"content":[36],"relevant":[37],"personalized":[38],"speech":[39,167],"synthesis":[40],"for":[41,84,130],"rapid":[42,69],"achieved":[46],"significant":[47],"performance":[48],"breakthrough":[49],"a":[51,101,106],"hybrid":[52],"[2].":[54],"In":[55,112,146],"this":[56],"paper,":[57],"answer":[59],"following":[61],"two":[62],"questions:":[63],"First,":[64],"how":[65],"effectively":[67],"perform":[68],"RNN-T.":[74],"Second,":[75],"whether":[76],"our":[77],"previously":[78],"approach":[80],"is":[81],"still":[82],"beneficial":[83],"RNN-T":[86,110],"what":[88],"are":[89],"modification":[91],"distinct":[93],"observations.":[94],"We":[95,169],"apply":[96,171],"methodology":[99],"task":[104],"state-of-art":[107],"presentation":[108],"transcription":[109],"system.":[111],"1":[114,142],"min":[115,143,149],"setup,":[116,150],"it":[117,151],"yields":[118,152],"11.58":[119],"%":[120,123,154,157],"or":[121,155],"7.95":[122],"relative":[124,158],"word":[125],"error":[126],"rate":[127],"(WER)":[128],"reduction":[129],"sup/unsup":[132,182],"adaptation,":[133],"comparing":[134],"negligible":[137],"gain":[138,163],"when":[139],"adapting":[140],"with":[141],"source":[144,166],"speech.":[145],"10":[148],"15.71":[153],"8.00":[156],"WER":[159],"reduction,":[160],"doubling":[161],"adaptation.":[168,183],"further":[170],"various":[172],"filtering":[174],"techniques":[175],"significantly":[177],"bridge":[178],"gap":[180],"between":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}