{"id":"https://openalex.org/W3024464021","doi":"https://doi.org/10.1109/cisp-bmei51763.2020.9263564","title":"You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation","display_name":"You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation","publication_year":2020,"publication_date":"2020-10-17","ids":{"openalex":"https://openalex.org/W3024464021","doi":"https://doi.org/10.1109/cisp-bmei51763.2020.9263564","mag":"3024464021"},"language":"en","primary_location":{"id":"doi:10.1109/cisp-bmei51763.2020.9263564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cisp-bmei51763.2020.9263564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.07157","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Aleksandr Laptev","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Aleksandr Laptev","raw_affiliation_strings":["ITMO University,St. Petersburg,Russia,197101"],"affiliations":[{"raw_affiliation_string":"ITMO University,St. Petersburg,Russia,197101","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Roman Korostik","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Roman Korostik","raw_affiliation_strings":["ITMO University,St. Petersburg,Russia,197101"],"affiliations":[{"raw_affiliation_string":"ITMO University,St. Petersburg,Russia,197101","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Aleksey Svischev","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Aleksey Svischev","raw_affiliation_strings":["ITMO University,St. Petersburg,Russia,197101"],"affiliations":[{"raw_affiliation_string":"ITMO University,St. Petersburg,Russia,197101","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Andrei Andrusenko","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Andrei Andrusenko","raw_affiliation_strings":["ITMO University,St. Petersburg,Russia,197101"],"affiliations":[{"raw_affiliation_string":"ITMO University,St. Petersburg,Russia,197101","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ivan Medennikov","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Ivan Medennikov","raw_affiliation_strings":["ITMO University,St. Petersburg,Russia,197101"],"affiliations":[{"raw_affiliation_string":"ITMO University,St. Petersburg,Russia,197101","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"last","author":{"id":null,"display_name":"Sergey Rybin","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Sergey Rybin","raw_affiliation_strings":["ITMO University,St. Petersburg,Russia,197101"],"affiliations":[{"raw_affiliation_string":"ITMO University,St. Petersburg,Russia,197101","institution_ids":["https://openalex.org/I173089394"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I173089394"],"apc_list":null,"apc_paid":null,"fwci":3.017,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.9280702,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"439","last_page":"444"},"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/T11309","display_name":"Music and Audio Processing","score":0.9958000183105469,"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/training-set","display_name":"Training set","score":0.57669997215271},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.569100022315979},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41589999198913574},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.40130001306533813},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3862000107765198},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3752000033855438},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3628000020980835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7799000144004822},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7545999884605408},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.57669997215271},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.569100022315979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4562999904155731},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41589999198913574},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3862000107765198},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3628000020980835},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3513999879360199},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.3409999907016754},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.27480000257492065},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.25929999351501465}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cisp-bmei51763.2020.9263564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cisp-bmei51763.2020.9263564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.07157","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.07157","pdf_url":"https://arxiv.org/pdf/2005.07157","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.07157","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.07157","pdf_url":"https://arxiv.org/pdf/2005.07157","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2170212447","https://openalex.org/W2936774411","https://openalex.org/W2944255943","https://openalex.org/W2962780374","https://openalex.org/W2963091184","https://openalex.org/W2963250244","https://openalex.org/W2963581463","https://openalex.org/W2963609956","https://openalex.org/W2963931415","https://openalex.org/W2964243274","https://openalex.org/W2972818416","https://openalex.org/W2972882294","https://openalex.org/W2973132140","https://openalex.org/W3008480565","https://openalex.org/W3015440759","https://openalex.org/W3015922793","https://openalex.org/W3018441253","https://openalex.org/W4395958986","https://openalex.org/W6623517193","https://openalex.org/W6640963894","https://openalex.org/W6713762819","https://openalex.org/W6739901393","https://openalex.org/W6750489868","https://openalex.org/W6755300632","https://openalex.org/W6756385397","https://openalex.org/W6763316926","https://openalex.org/W6768158615","https://openalex.org/W6770506093","https://openalex.org/W6771907615","https://openalex.org/W6791127467"],"related_works":[],"abstract_inverted_index":{"Data":[0],"augmentation":[1,93],"is":[2,69],"one":[3],"of":[4,104],"the":[5,19,51,65,91,95,102],"most":[6],"effective":[7],"ways":[8],"to":[9,18,56,79],"make":[10],"end-to-end":[11,77,151],"automatic":[12],"speech":[13,33,55],"recognition":[14,59],"(ASR)":[15],"perform":[16],"close":[17],"conventional":[20],"hybrid":[21,81],"approach,":[22],"especially":[23],"when":[24,64],"dealing":[25],"with":[26,53,94,115,121,158],"low-resource":[27],"tasks.":[28],"Using":[29],"recent":[30],"advances":[31],"in":[32],"synthesis":[34],"(text-to-speech,":[35],"or":[36],"TTS),":[37],"we":[38,89],"build":[39],"our":[40,116,126],"TTS":[41],"system":[42,145],"on":[43,107,154],"an":[44,76,85,122],"ASR":[45,109,152],"training":[46,66],"database":[47],"and":[48,135,163],"then":[49],"extend":[50],"data":[52,67],"synthesized":[54],"train":[57],"a":[58,129,140,147],"model.":[60],"We":[61,99],"argue":[62],"that,":[63],"amount":[68],"relatively":[70],"low,":[71],"this":[72],"approach":[73,127],"can":[74],"allow":[75],"model":[78],"reach":[80],"systems'":[82],"quality.":[83],"For":[84],"artificial":[86],"low-to-medium-resource":[87],"setup,":[88],"compare":[90],"proposed":[92],"semi-supervised":[96,130],"learning":[97],"technique.":[98],"also":[100],"investigate":[101],"influence":[103],"vocoder":[105],"usage":[106],"final":[108],"performance":[110],"by":[111],"comparing":[112],"Griffin-Lim":[113],"algorithm":[114],"modified":[117],"LPCNet.":[118],"When":[119],"applied":[120],"external":[123],"language":[124],"model,":[125],"outperforms":[128],"setup":[131],"for":[132,150,161,165],"LibriSpeech":[133,155],"test-clean":[134,162],"only":[136],"33%":[137],"worse":[138],"than":[139],"comparable":[141],"supervised":[142],"setup.":[143],"Our":[144],"establishes":[146],"competitive":[148],"result":[149],"trained":[153],"train-clean-100":[156],"set":[157],"WER":[159],"4.3%":[160],"13.5%":[164],"test-other.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-05-21T00:00:00"}