{"id":"https://openalex.org/W3162244132","doi":"https://doi.org/10.1109/icassp39728.2021.9414778","title":"Using Synthetic Audio to Improve the Recognition of Out-of-Vocabulary Words in End-to-End Asr Systems","display_name":"Using Synthetic Audio to Improve the Recognition of Out-of-Vocabulary Words in End-to-End Asr Systems","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162244132","doi":"https://doi.org/10.1109/icassp39728.2021.9414778","mag":"3162244132"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5013736436","display_name":"Xianrui Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xianrui Zheng","raw_affiliation_strings":["University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"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/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":"Yulan Liu","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091451196","display_name":"Deniz Gunceler","orcid":null},"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":"Deniz Gunceler","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017400582","display_name":"Daniel Willett","orcid":null},"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":"Daniel Willett","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.5938,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.9749076,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5674","last_page":"5678"},"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":0.9968000054359436,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9966999888420105,"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":0.814022421836853},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7368122935295105},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6635262966156006},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6371831297874451},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5373232960700989},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5295373201370239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5232588052749634},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.49826645851135254},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.497226744890213},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.48626458644866943},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.44407594203948975},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42003169655799866},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38758528232574463}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.814022421836853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7368122935295105},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6635262966156006},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6371831297874451},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5373232960700989},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5295373201370239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5232588052749634},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.49826645851135254},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.497226744890213},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.48626458644866943},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.44407594203948975},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42003169655799866},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38758528232574463},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1586532344","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W2327501763","https://openalex.org/W2560647685","https://openalex.org/W2898727538","https://openalex.org/W2899901795","https://openalex.org/W2912937645","https://openalex.org/W2916997151","https://openalex.org/W2962760690","https://openalex.org/W2963250244","https://openalex.org/W2963362078","https://openalex.org/W3006752097","https://openalex.org/W3008037978","https://openalex.org/W3008480565","https://openalex.org/W3015449694","https://openalex.org/W3091322135","https://openalex.org/W3094667432","https://openalex.org/W3096815019","https://openalex.org/W3107298252","https://openalex.org/W6623517193","https://openalex.org/W6635078382","https://openalex.org/W6638749077","https://openalex.org/W6640059789","https://openalex.org/W6755891724","https://openalex.org/W6756385397","https://openalex.org/W6786599525"],"related_works":["https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W1999699871","https://openalex.org/W2145230572","https://openalex.org/W2021633306","https://openalex.org/W2006801911","https://openalex.org/W2146197305","https://openalex.org/W2166312020","https://openalex.org/W2033669961","https://openalex.org/W2134950286"],"abstract_inverted_index":{"Today,":[0],"many":[1],"state-of-the-art":[2],"automatic":[3],"speech":[4],"recognition":[5,89],"(ASR)":[6],"systems":[7],"apply":[8],"all-neural":[9],"models":[10,31],"that":[11,50],"map":[12],"audio":[13,79],"to":[14,76,86],"word":[15,153],"sequences":[16],"trained":[17],"end-to-end":[18],"along":[19],"one":[20],"global":[21],"optimisation":[22],"criterion":[23],"in":[24,41],"a":[25,72,92,150],"fully":[26],"data":[27,134,138],"driven":[28],"fashion.":[29],"These":[30],"allow":[32],"high":[33],"precision":[34],"ASR":[35],"for":[36,80],"domains":[37],"and":[38,63,120,135],"words":[39,49,62,100,162],"represented":[40,57],"the":[42,88,103,109,112,121,128,146,167],"training":[43,133],"material":[44],"but":[45],"have":[46],"difficulties":[47],"recognising":[48],"are":[51,118],"rarely":[52],"or":[53],"not":[54],"at":[55],"all":[56],"during":[58],"training,":[59],"i.e.":[60],"trending":[61],"new":[64],"named":[65],"entities.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70],"use":[71],"text-to-speech":[73],"(TTS)":[74],"engine":[75],"provide":[77],"synthetic":[78,137],"out-of-vocabulary":[81],"(OOV)":[82],"words.":[83,114],"We":[84],"aim":[85],"boost":[87],"accuracy":[90],"of":[91],"recurrent":[93],"neural":[94],"network":[95],"transducer":[96],"(RNN-T)":[97],"on":[98,111,130,145,158,166],"OOV":[99,161],"by":[101,126],"using":[102],"extra":[104,136],"audio-text":[105],"pairs,":[106],"while":[107],"maintaining":[108],"performance":[110,123],"non-OOV":[113],"Different":[115],"regularisation":[116],"techniques":[117],"explored":[119],"best":[122],"is":[124],"achieved":[125],"fine-tuning":[127],"RNN-T":[129],"both":[131],"original":[132],"with":[139],"elastic":[140],"weight":[141],"consolidation":[142],"(EWC)":[143],"applied":[144],"encoder.":[147],"This":[148],"yields":[149],"57%":[151],"relative":[152],"error":[154],"rate":[155],"(WER)":[156],"reduction":[157],"utterances":[159],"containing":[160],"without":[163],"any":[164],"degradation":[165],"whole":[168],"test":[169],"set.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}