{"id":"https://openalex.org/W3015280134","doi":"https://doi.org/10.1109/icassp40776.2020.9053831","title":"Improving Speech Recognition Using Consistent Predictions on Synthesized Speech","display_name":"Improving Speech Recognition Using Consistent Predictions on Synthesized Speech","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015280134","doi":"https://doi.org/10.1109/icassp40776.2020.9053831","mag":"3015280134"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053831","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5025935520","display_name":"Gary Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Gary Wang","raw_affiliation_strings":["Simon Fraser University"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102902866","display_name":"Andrew Rosenberg","orcid":"https://orcid.org/0000-0003-1780-4390"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Rosenberg","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002433660","display_name":"Zhehuai Chen","orcid":"https://orcid.org/0000-0003-4400-5340"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhehuai Chen","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433648","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-9505-1833"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010253402","display_name":"Yonghui Wu","orcid":"https://orcid.org/0000-0002-6780-6135"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yonghui Wu","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103874391","display_name":"Pedro J. Moreno","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pedro Moreno","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5025935520"],"corresponding_institution_ids":["https://openalex.org/I18014758"],"apc_list":null,"apc_paid":null,"fwci":6.0706,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.96919495,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7029","last_page":"7033"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9988999962806702,"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":0.9987000226974487,"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/speech-recognition","display_name":"Speech recognition","score":0.8111741542816162},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7331386804580688},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.599217414855957},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5460465550422668},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5041590929031372},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.49746039509773254},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4936336278915405},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4809812307357788},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.43947717547416687},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3237723112106323},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06658154726028442}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8111741542816162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7331386804580688},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.599217414855957},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5460465550422668},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5041590929031372},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.49746039509773254},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4936336278915405},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4809812307357788},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.43947717547416687},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3237723112106323},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06658154726028442},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053831","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2095705004","https://openalex.org/W2102113734","https://openalex.org/W2119717200","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2591927543","https://openalex.org/W2606711863","https://openalex.org/W2743945814","https://openalex.org/W2799800213","https://openalex.org/W2808706139","https://openalex.org/W2883586237","https://openalex.org/W2898727538","https://openalex.org/W2911876655","https://openalex.org/W2936774411","https://openalex.org/W2938947737","https://openalex.org/W2942203175","https://openalex.org/W2944255943","https://openalex.org/W2952711665","https://openalex.org/W2962699523","https://openalex.org/W2962826786","https://openalex.org/W2963216553","https://openalex.org/W2963382687","https://openalex.org/W2963432880","https://openalex.org/W2963609956","https://openalex.org/W2963739817","https://openalex.org/W2964121744","https://openalex.org/W2964159205","https://openalex.org/W2964281804","https://openalex.org/W2972359262","https://openalex.org/W2972889948","https://openalex.org/W2978426779","https://openalex.org/W3008480565","https://openalex.org/W3103005696","https://openalex.org/W4299838440","https://openalex.org/W6629717138","https://openalex.org/W6631190155","https://openalex.org/W6674330103","https://openalex.org/W6675365184","https://openalex.org/W6695909211","https://openalex.org/W6713762819","https://openalex.org/W6734815144","https://openalex.org/W6736346607","https://openalex.org/W6742632731","https://openalex.org/W6752888775","https://openalex.org/W6753186555","https://openalex.org/W6756385397","https://openalex.org/W6761827036","https://openalex.org/W6762242920","https://openalex.org/W6762913911"],"related_works":["https://openalex.org/W2496295964","https://openalex.org/W1976952689","https://openalex.org/W2336887028","https://openalex.org/W1911859126","https://openalex.org/W2131711534","https://openalex.org/W642007152","https://openalex.org/W2341426843","https://openalex.org/W1583620810","https://openalex.org/W4387712795","https://openalex.org/W2110852049"],"abstract_inverted_index":{"Speech":[0],"synthesis":[1],"has":[2],"advanced":[3],"to":[4,10,17,29,38,55],"the":[5],"point":[6],"of":[7,74,80,89,96],"being":[8],"close":[9],"indistinguishable":[11],"from":[12],"human":[13,42],"speech.":[14,43],"However,":[15],"efforts":[16],"train":[18],"speech":[19,59,63],"recognition":[20,64],"systems":[21],"on":[22,71,93,112],"synthesized":[23,32,58],"utterances":[24],"have":[25],"not":[26],"been":[27],"able":[28],"show":[30],"that":[31,49,69,101],"data":[33],"can":[34,115],"be":[35,116],"effectively":[36],"used":[37],"augment":[39],"or":[40],"replace":[41],"In":[44],"this":[45,103],"work,":[46],"we":[47],"demonstrate":[48],"promoting":[50],"consistent":[51],"predictions":[52],"in":[53,119],"response":[54],"real":[56],"and":[57],"enables":[60],"significantly":[61],"improved":[62],"performance.":[65],"We":[66],"also":[67],"find":[68],"training":[70],"460":[72],"hours":[73,79,95],"LibriSpeech":[75],"augmented":[76],"with":[77,102],"500":[78],"transcripts":[81],"(without":[82],"audio)":[83],"performance":[84],"is":[85,107],"within":[86],"0.2%":[87],"WER":[88],"a":[90],"system":[91],"trained":[92],"960":[94],"transcribed":[97,113],"audio.":[98],"This":[99],"suggests":[100],"approach,":[104],"when":[105],"there":[106],"sufficient":[108],"text":[109],"available,":[110],"reliance":[111],"audio":[114],"cut":[117],"nearly":[118],"half.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":5}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}