{"id":"https://openalex.org/W3110101984","doi":"https://doi.org/10.21437/interspeech.2021-198","title":"Bootstrap an End-to-End ASR System by Multilingual Training, Transfer Learning, Text-to-Text Mapping and Synthetic Audio","display_name":"Bootstrap an End-to-End ASR System by Multilingual Training, Transfer Learning, Text-to-Text Mapping and Synthetic Audio","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3110101984","doi":"https://doi.org/10.21437/interspeech.2021-198","mag":"3110101984"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-198","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.12696","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087447838","display_name":"Manuel Giollo","orcid":"https://orcid.org/0000-0001-9434-2383"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Manuel Giollo","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091451196","display_name":"Deniz Gunceler","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Deniz Gunceler","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768704","display_name":"Yulan Liu","orcid":"https://orcid.org/0000-0003-3320-2381"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yulan Liu","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017400582","display_name":"Daniel Willett","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Willett","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210089985"],"apc_list":null,"apc_paid":null,"fwci":0.1466,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.32443876,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2416","last_page":"2420"},"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":0.9986000061035156,"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/T10028","display_name":"Topic Modeling","score":0.9975000023841858,"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":0.7832026481628418},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.7709070444107056},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6026819944381714},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6009281873703003},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5826095342636108},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5659578442573547},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5573345422744751},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5431801676750183},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5252746343612671},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4719630479812622},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4685578942298889},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4216269552707672},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4161868691444397},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1473972499370575},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08115950226783752}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7832026481628418},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.7709070444107056},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6026819944381714},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6009281873703003},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5826095342636108},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5659578442573547},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5573345422744751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5431801676750183},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5252746343612671},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4719630479812622},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4685578942298889},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4216269552707672},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4161868691444397},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1473972499370575},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08115950226783752},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-198","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.12696","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.12696","pdf_url":"https://arxiv.org/pdf/2011.12696","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},{"id":"mag:3110101984","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.12696","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.12696","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.12696","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.12696","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.12696","pdf_url":"https://arxiv.org/pdf/2011.12696","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3110101984.pdf","grobid_xml":"https://content.openalex.org/works/W3110101984.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W1934041838","https://openalex.org/W2090755665","https://openalex.org/W2118947254","https://openalex.org/W2262393948","https://openalex.org/W2327501763","https://openalex.org/W2507739667","https://openalex.org/W2515439472","https://openalex.org/W2894835365","https://openalex.org/W2912937645","https://openalex.org/W2916997151","https://openalex.org/W2936774411","https://openalex.org/W2941649920","https://openalex.org/W2962760690","https://openalex.org/W2962826786","https://openalex.org/W2963250244","https://openalex.org/W2963303951","https://openalex.org/W2971840980","https://openalex.org/W3006926732","https://openalex.org/W3008480565","https://openalex.org/W3015449694","https://openalex.org/W3016256870","https://openalex.org/W3095184753","https://openalex.org/W3096032230","https://openalex.org/W3162244132"],"related_works":["https://openalex.org/W3198047825","https://openalex.org/W3015449694","https://openalex.org/W2952711665","https://openalex.org/W2972889948","https://openalex.org/W3016188195","https://openalex.org/W3107298252","https://openalex.org/W2973227840","https://openalex.org/W3156762052","https://openalex.org/W3015747801","https://openalex.org/W3034335198","https://openalex.org/W3094180720","https://openalex.org/W2809035663","https://openalex.org/W2913851961","https://openalex.org/W244415383","https://openalex.org/W2936832667","https://openalex.org/W2891616026","https://openalex.org/W3166538612","https://openalex.org/W3016042119","https://openalex.org/W3161525333","https://openalex.org/W2998386507"],"abstract_inverted_index":{"Bootstrapping":[0],"speech":[1,80],"recognition":[2,81],"on":[3],"limited":[4],"data":[5,37,50,145],"resources":[6,93],"has":[7],"been":[8],"an":[9,75],"area":[10],"of":[11,70,143],"active":[12],"research":[13],"for":[14,136],"long.":[15],"The":[16,151],"recent":[17],"transition":[18],"to":[19,35,73,132,164,176],"all-neural":[20],"models":[21,32],"and":[22,63,124,181],"end-to-end":[23],"(E2E)":[24],"training":[25],"brought":[26],"along":[27],"particular":[28],"challenges":[29],"as":[30,51,53,98,100],"these":[31],"are":[33],"known":[34],"be":[36,149],"hungry,":[38],"but":[39],"also":[40],"came":[41],"with":[42,140],"opportunities":[43],"around":[44],"language-agnostic":[45],"representations":[46,57],"derived":[47],"from":[48,104,115],"multilingual":[49,117],"well":[52,99],"shared":[54],"word-piece":[55],"output":[56],"across":[58],"languages":[59,97],"that":[60,112,146],"share":[61],"script":[62],"roots.":[64],"We":[65],"investigate":[66],"here":[67],"the":[68,85,91,101,144,165,177,182],"effectiveness":[69],"different":[71],"strategies":[72],"bootstrap":[74,133],"RNN-Transducer":[76],"(RNN-T)":[77],"based":[78],"automatic":[79],"(ASR)":[82],"system":[83,153],"in":[84,95],"low":[86],"resource":[87],"regime,":[88],"while":[89],"exploiting":[90],"abundant":[92],"available":[94],"other":[96],"synthetic":[102,125,184],"audio":[103,126],"a":[105,116,120,134,137,141,155],"text-to-speech":[106],"(TTS)":[107],"engine.":[108],"Our":[109],"experiments":[110],"demonstrate":[111],"transfer":[113],"learning":[114],"model,":[118],"using":[119],"post-ASR":[121,178],"text-to-text":[122,179],"mapping":[123],"deliver":[127],"additive":[128],"improvements,":[129],"allowing":[130],"us":[131],"model":[135],"new":[138],"language":[139],"fraction":[142],"would":[147],"otherwise":[148],"needed.":[150],"best":[152],"achieved":[154],"46%":[156],"relative":[157,171],"word":[158],"error":[159],"rate":[160],"(WER)":[161],"reduction":[162],"compared":[163],"monolingual":[166],"baseline,":[167],"among":[168],"which":[169],"25%":[170],"WER":[172],"improvement":[173],"is":[174],"attributed":[175],"mappings":[180],"TTS":[183],"data.":[185]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}