{"id":"https://openalex.org/W2886246524","doi":"https://doi.org/10.1109/slt.2018.8639610","title":"Toward Domain-Invariant Speech Recognition via Large Scale Training","display_name":"Toward Domain-Invariant Speech Recognition via Large Scale Training","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2886246524","doi":"https://doi.org/10.1109/slt.2018.8639610","mag":"2886246524"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1808.05312","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000078382","display_name":"Arun Narayanan","orcid":"https://orcid.org/0009-0008-3325-8928"},"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":true,"raw_author_name":"Arun Narayanan","raw_affiliation_strings":["Google, USA","Google  USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google  USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091715883","display_name":"Ananya Misra","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":"Ananya Misra","raw_affiliation_strings":["Google, USA","Google  USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google  USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032798707","display_name":"Khe Chai Sim","orcid":"https://orcid.org/0000-0002-0866-2223"},"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":"Khe Chai Sim","raw_affiliation_strings":["Google, USA","Google  USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google  USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051090720","display_name":"Golan Pundak","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":"Golan Pundak","raw_affiliation_strings":["Google, USA","Google  USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google  USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101403998","display_name":"Anshuman Tripathi","orcid":"https://orcid.org/0000-0002-4902-3719"},"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":"Anshuman Tripathi","raw_affiliation_strings":["Google, USA","Google  USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google  USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111926790","display_name":"Mohamed Elfeky","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":"Mohamed Elfeky","raw_affiliation_strings":["Google, USA","Google  USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google  USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037705635","display_name":"Parisa Haghani","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":"Parisa Haghani","raw_affiliation_strings":["Google, USA","Google  USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google  USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032931723","display_name":"Trevor Strohman","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":"Trevor Strohman","raw_affiliation_strings":["Google, USA","Google  USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google  USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049614700","display_name":"Michiel Bacchiani","orcid":"https://orcid.org/0000-0003-4527-0197"},"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":"Michiel Bacchiani","raw_affiliation_strings":["Google, USA","Google  USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google  USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5000078382"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.08623937,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"441","last_page":"447"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.991100013256073,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9884999990463257,"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":0.784421443939209},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6791712045669556},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.5704447031021118},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5606064796447754},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5326877236366272},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5184676051139832},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49562394618988037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45440831780433655},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43579670786857605},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.4243066906929016},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.375239759683609},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10360527038574219}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.784421443939209},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6791712045669556},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5704447031021118},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5606064796447754},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5326877236366272},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5184676051139832},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49562394618988037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45440831780433655},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43579670786857605},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.4243066906929016},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.375239759683609},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10360527038574219},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/slt.2018.8639610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1808.05312","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.05312","pdf_url":"https://arxiv.org/pdf/1808.05312","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":"","raw_type":"text"},{"id":"mag:2886246524","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1808.05312.pdf","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.1808.05312","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1808.05312","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1808.05312","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.05312","pdf_url":"https://arxiv.org/pdf/1808.05312","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2886246524.pdf"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1502560247","https://openalex.org/W1569447338","https://openalex.org/W1885680957","https://openalex.org/W1985371235","https://openalex.org/W1987971958","https://openalex.org/W2024490156","https://openalex.org/W2033256038","https://openalex.org/W2035576074","https://openalex.org/W2051224630","https://openalex.org/W2056786202","https://openalex.org/W2099547538","https://openalex.org/W2141411743","https://openalex.org/W2166637769","https://openalex.org/W2288645994","https://openalex.org/W2293634267","https://openalex.org/W2295582178","https://openalex.org/W2296545762","https://openalex.org/W2402144811","https://openalex.org/W2510616059","https://openalex.org/W2510867321","https://openalex.org/W2515439472","https://openalex.org/W2550246519","https://openalex.org/W2589857635","https://openalex.org/W2593768305","https://openalex.org/W2606722458","https://openalex.org/W2617258110","https://openalex.org/W2748545504","https://openalex.org/W2748584437","https://openalex.org/W2769025471","https://openalex.org/W2786459654","https://openalex.org/W2889423969","https://openalex.org/W2951327905","https://openalex.org/W2953212265","https://openalex.org/W2962894366","https://openalex.org/W2963266252","https://openalex.org/W2963838962","https://openalex.org/W2963980299","https://openalex.org/W2964138484","https://openalex.org/W6630236247","https://openalex.org/W6633847657","https://openalex.org/W6637618735","https://openalex.org/W6688428952","https://openalex.org/W6696934422","https://openalex.org/W6697274609","https://openalex.org/W6713134421","https://openalex.org/W6728910023","https://openalex.org/W6729491343","https://openalex.org/W6748211734","https://openalex.org/W6748426227"],"related_works":["https://openalex.org/W2963122170","https://openalex.org/W3010079784","https://openalex.org/W2749784707","https://openalex.org/W2737108017","https://openalex.org/W3011500442","https://openalex.org/W2804758356","https://openalex.org/W2964245029","https://openalex.org/W3104648745","https://openalex.org/W2796010067","https://openalex.org/W2787133659","https://openalex.org/W3097148135","https://openalex.org/W2981590980","https://openalex.org/W3008876072","https://openalex.org/W3094861840","https://openalex.org/W2994785103","https://openalex.org/W2941619235","https://openalex.org/W3093511653","https://openalex.org/W2885724687","https://openalex.org/W1486143877","https://openalex.org/W3014973941"],"abstract_inverted_index":{"Current":[0],"state-of-the-art":[1],"automatic":[2],"speech":[3],"recognition":[4],"systems":[5],"are":[6,26],"trained":[7,68,105,174],"to":[8,82,113,122,138],"work":[9,41],"in":[10,28,198],"specific":[11,114],"`domains',":[12],"defined":[13],"based":[14],"on":[15],"factors":[16],"like":[17,85,128],"application,":[18],"sampling":[19,91],"rate":[20],"and":[21,90,126,130,141,193],"codec.":[22],"When":[23],"such":[24,99,134,191],"recognizers":[25],"used":[27],"conditions":[29,140],"that":[30,149,195],"do":[31],"not":[32],"match":[33,168],"the":[34,43,188],"training":[35,58,81],"domain,":[36,162],"performance":[37,169],"significantly":[38],"drops.":[39],"This":[40],"explores":[42],"idea":[44],"of":[45,72,157,170,187,190],"building":[46],"a":[47,100,102,160,171],"single":[48,117],"domain-invariant":[49,165],"model":[50,103,118,166,173],"for":[51,143],"varied":[52],"use-cases":[53],"by":[54,150],"combining":[55],"large":[56],"scale":[57],"data":[59,158],"from":[60,159,175],"multiple":[61,123],"application":[62,124],"domains.":[63],"Our":[64,93],"final":[65],"system":[66],"is":[67,77],"using":[69,151,177],"162,000":[70],"hours":[71,156],"speech.":[73],"Additionally,":[74],"each":[75],"utterance":[76],"artificially":[78],"distorted":[79],"during":[80],"simulate":[83],"effects":[84],"background":[86],"noise,":[87],"codec":[88],"distortion,":[89],"rates.":[92],"results":[94],"show":[95,148],"that,":[96],"even":[97],"at":[98],"scale,":[101],"thus":[104],"works":[106],"almost":[107],"as":[108,110,152,154,180],"well":[109],"those":[111],"fine-tuned":[112],"subsets:":[115],"A":[116],"can":[119,167],"be":[120],"robust":[121],"domains,":[125],"variations":[127],"codecs":[129],"noise.":[131],"More":[132],"importantly,":[133],"models":[135,192],"generalize":[136],"better":[137],"unseen":[139],"allow":[142],"rapid":[144],"adaptation":[145],"-":[146],"we":[147],"little":[153],"10":[155],"new":[161],"an":[163],"adapted":[164],"domain-specific":[172],"scratch":[176],"70":[178],"times":[179],"much":[181],"data.":[182],"We":[183],"also":[184],"highlight":[185],"some":[186],"limitations":[189],"areas":[194],"need":[196],"addressing":[197],"future":[199],"work.":[200]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}