{"id":"https://openalex.org/W3168872064","doi":"https://doi.org/10.21437/interspeech.2021-1882","title":"SynthASR: Unlocking Synthetic Data for Speech Recognition","display_name":"SynthASR: Unlocking Synthetic Data for Speech Recognition","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3168872064","doi":"https://doi.org/10.21437/interspeech.2021-1882","mag":"3168872064"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1882","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1882","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/2106.07803","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029022979","display_name":"Amin Fazel","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Amin Fazel","raw_affiliation_strings":["Samsung (South Korea), Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung (South Korea), Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362557","display_name":"Wei Yang","orcid":"https://orcid.org/0000-0003-2272-6796"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768704","display_name":"Yulan Liu","orcid":"https://orcid.org/0000-0003-3320-2381"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yulan Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027755752","display_name":"Roberto Barra-Chicote","orcid":"https://orcid.org/0000-0003-0844-7037"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roberto Barra-Chicote","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006074231","display_name":"Yixiong Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixiong Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090454997","display_name":"Roland Maas","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":"Roland Maas","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/A5012153296","display_name":"Jasha Droppo","orcid":"https://orcid.org/0000-0001-6097-0090"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jasha Droppo","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2931,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50222755,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"896","last_page":"900"},"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":0.9955000281333923,"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":0.994700014591217,"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":0.8167628049850464},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7522691488265991},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6244578957557678},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.514831006526947},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45443055033683777},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.44184422492980957},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4266435205936432}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8167628049850464},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7522691488265991},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6244578957557678},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.514831006526947},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45443055033683777},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.44184422492980957},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4266435205936432},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-1882","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1882","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:2106.07803","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.07803","pdf_url":"https://arxiv.org/pdf/2106.07803","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3168872064","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.07803.pdf","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.2106.07803","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.07803","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:2106.07803","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.07803","pdf_url":"https://arxiv.org/pdf/2106.07803","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3168872064.pdf","grobid_xml":"https://content.openalex.org/works/W3168872064.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2064675550","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2136439176","https://openalex.org/W2283463896","https://openalex.org/W2327501763","https://openalex.org/W2401932923","https://openalex.org/W2696967604","https://openalex.org/W2788388592","https://openalex.org/W2912937645","https://openalex.org/W2936774411","https://openalex.org/W2940200615","https://openalex.org/W2941649920","https://openalex.org/W2963250244","https://openalex.org/W2963803379","https://openalex.org/W2964121744","https://openalex.org/W2991213871","https://openalex.org/W3008037978","https://openalex.org/W3013020904","https://openalex.org/W3015265920","https://openalex.org/W3015449694","https://openalex.org/W3015654635","https://openalex.org/W3015927303","https://openalex.org/W3015995734","https://openalex.org/W3016234571","https://openalex.org/W3111551290","https://openalex.org/W3152221657","https://openalex.org/W3162244132"],"related_works":["https://openalex.org/W3182974804","https://openalex.org/W3169723574","https://openalex.org/W3180992661","https://openalex.org/W2572023240","https://openalex.org/W3037291366","https://openalex.org/W2992448548","https://openalex.org/W2913566369","https://openalex.org/W1504449689","https://openalex.org/W3186546663","https://openalex.org/W3105804405","https://openalex.org/W2804884650","https://openalex.org/W3163339532","https://openalex.org/W3095773170","https://openalex.org/W3155343771","https://openalex.org/W3198413388","https://openalex.org/W2940526039","https://openalex.org/W3108266107","https://openalex.org/W3165957370","https://openalex.org/W3163142165","https://openalex.org/W3155168732"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"automatic":[2],"speech":[3,47,68],"recognition":[4,147],"(ASR)":[5],"models":[6,136,178],"have":[7],"recently":[8],"demonstrated":[9],"superior":[10],"performance":[11,148],"over":[12],"the":[13,43,50,141,146,173,184],"traditional":[14],"hybrid":[15],"ASR":[16,21,70,84,134,177],"models.":[17],"Training":[18],"an":[19],"E2E":[20,176],"model":[22,85],"requires":[23],"a":[24,94,105,126],"large":[25],"amount":[26],"of":[27,107,129],"data":[28,76,111],"which":[29],"is":[30,77],"not":[31],"only":[32],"expensive":[33],"but":[34],"may":[35],"also":[36],"raise":[37],"dependency":[38,187],"on":[39,122,149,159,188],"production":[40,189],"data.":[41,190],"At":[42],"same":[44],"time,":[45],"synthetic":[46,67,138],"generated":[48],"by":[49,104,152],"state-of-the-art":[51,174],"text-to-speech":[52],"(TTS)":[53],"engines":[54],"has":[55],"advanced":[56],"to":[57,65,81,99],"near-human":[58],"naturalness.":[59],"In":[60,87,118],"this":[61],"work,":[62],"we":[63,89],"propose":[64],"utilize":[66],"for":[69,83,125,179],"training":[71,97,133,144,172],"(SynthASR)":[72],"in":[73,171],"applications":[74,181],"where":[75],"sparse":[78],"or":[79],"hard":[80],"get":[82],"training.":[86],"addition,":[88],"apply":[90],"continual":[91],"learning":[92],"with":[93,137],"novel":[95],"multi-stage":[96,143],"strategy":[98],"address":[100],"catastrophic":[101],"forgetting,":[102],"achieved":[103],"mix":[106],"weighted":[108],"multi-style":[109],"training,":[110],"augmentation,":[112],"encoder":[113],"freezing,":[114],"and":[115,186],"parameter":[116],"regularization.":[117],"our":[119],"experiments":[120],"conducted":[121],"in-house":[123],"datasets":[124],"new":[127,150,180],"application":[128,151],"recognizing":[130],"medication":[131],"names,":[132],"RNN-T":[135],"audio":[139],"via":[140],"proposed":[142],"improved":[145],"more":[153],"than":[154],"65%":[155],"relative,":[156],"without":[157],"degradation":[158],"existing":[160],"general":[161],"applications.":[162],"Our":[163],"observations":[164],"show":[165],"that":[166],"SynthASR":[167],"holds":[168],"great":[169],"promise":[170],"large-scale":[175],"while":[182],"reducing":[183],"costs":[185]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}