{"id":"https://openalex.org/W2975100556","doi":"https://doi.org/10.1109/asru46091.2019.9003990","title":"Speech Recognition with Augmented Synthesized Speech","display_name":"Speech Recognition with Augmented Synthesized Speech","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W2975100556","doi":"https://doi.org/10.1109/asru46091.2019.9003990","mag":"2975100556"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003990","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003990","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/1909.11699","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433430","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0001-8456-7335"},"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","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]},{"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","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102792436","display_name":"Jia Ye","orcid":"https://orcid.org/0000-0002-8000-4911"},"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":"Ye Jia","raw_affiliation_strings":["Google","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]},{"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","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035558261","display_name":"Zelin Wu","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":"Zelin Wu","raw_affiliation_strings":["Google","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"996","last_page":"1002"},"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/T10028","display_name":"Topic Modeling","score":0.9973000288009644,"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":0.9972000122070312,"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":0.8157303333282471},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7738246917724609},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5438897609710693},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.54143226146698},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.48559635877609253},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4829794466495514},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4546632170677185},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3973250985145569},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3890683650970459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36196956038475037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8157303333282471},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7738246917724609},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5438897609710693},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.54143226146698},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.48559635877609253},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4829794466495514},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4546632170677185},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3973250985145569},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3890683650970459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36196956038475037}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/asru46091.2019.9003990","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003990","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1909.11699","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.11699","pdf_url":"https://arxiv.org/pdf/1909.11699","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":"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:2975100556","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1909.11699","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1909.11699","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1909.11699","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1909.11699","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.11699","pdf_url":"https://arxiv.org/pdf/1909.11699","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":"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":0.5199999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2975100556.pdf","grobid_xml":"https://content.openalex.org/works/W2975100556.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1509793305","https://openalex.org/W1810943226","https://openalex.org/W1979651826","https://openalex.org/W2530486890","https://openalex.org/W2622263826","https://openalex.org/W2747467128","https://openalex.org/W2794490148","https://openalex.org/W2898727538","https://openalex.org/W2928941594","https://openalex.org/W2943543019","https://openalex.org/W2962699523","https://openalex.org/W2962824709","https://openalex.org/W2963568578","https://openalex.org/W2963796886","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W6748409065","https://openalex.org/W6752888775"],"related_works":["https://openalex.org/W2940200615","https://openalex.org/W2132877153","https://openalex.org/W601151541","https://openalex.org/W2120758120","https://openalex.org/W1589734697","https://openalex.org/W2007062874","https://openalex.org/W1940002922","https://openalex.org/W2099813353","https://openalex.org/W170174517","https://openalex.org/W2070893232","https://openalex.org/W2891426280","https://openalex.org/W2127127921","https://openalex.org/W2904141985","https://openalex.org/W2555946274","https://openalex.org/W344150399","https://openalex.org/W2140400559","https://openalex.org/W2071609901","https://openalex.org/W1652729136","https://openalex.org/W2061768620","https://openalex.org/W2936184970"],"abstract_inverted_index":{"Recent":[0],"success":[1],"of":[2,23,48,63,74,109],"the":[3,20,64,72,93,107],"Tacotron":[4],"speech":[5,17,30,36,40,76,80,102,124,149],"synthesis":[6,41,81],"architecture":[7,42],"and":[8,51,96],"its":[9],"variants":[10],"in":[11,142],"producing":[12],"natural":[13],"sounding":[14],"multi-speaker":[15,39],"synthesized":[16,65,134,153],"has":[18],"raised":[19],"exciting":[21],"possibility":[22],"replacing":[24],"expensive,":[25],"manually":[26],"transcribed,":[27],"domain-specific,":[28],"human":[29,148],"that":[31,121],"is":[32,127],"used":[33],"to":[34,91,123],"train":[35],"recognizers.":[37],"The":[38],"can":[43],"learn":[44],"latent":[45],"embedding":[46],"spaces":[47],"prosody,":[49],"speaker":[50],"style":[52],"variations":[53],"derived":[54],"from":[55,85],"input":[56],"acoustic":[57,95],"representations":[58],"thereby":[59],"allowing":[60],"for":[61,100,117],"manipulation":[62],"speech.":[66,154],"In":[67],"this":[68,110],"paper,":[69],"we":[70,105],"evaluate":[71],"feasibility":[73,108],"enhancing":[75],"recognition":[77,125],"performance":[78,126,143],"using":[79,82],"two":[83],"corpora":[84],"different":[86],"domains.":[87],"We":[88,119],"explore":[89],"algorithms":[90],"provide":[92],"necessary":[94],"lexical":[97],"diversity":[98],"needed":[99],"robust":[101],"recognition.":[103],"Finally,":[104],"demonstrate":[106],"approach":[111],"as":[112],"a":[113,139],"data":[114,132],"augmentation":[115],"strategy":[116],"domain-transfer.":[118],"find":[120],"improvements":[122],"achievable":[128],"by":[129],"augmenting":[130],"training":[131],"with":[133],"material.":[135],"However,":[136],"there":[137],"remains":[138],"substantial":[140],"gap":[141],"between":[144],"recognizers":[145],"trained":[146,151],"on":[147,152],"those":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}