{"id":"https://openalex.org/W3093502935","doi":"https://doi.org/10.21437/interspeech.2021-1758","title":"Rethinking Evaluation in ASR: Are Our Models Robust Enough?","display_name":"Rethinking Evaluation in ASR: Are Our Models Robust Enough?","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3093502935","doi":"https://doi.org/10.21437/interspeech.2021-1758","mag":"3093502935"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1758","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/2010.11745","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106542588","display_name":"Tatiana Likhomanenko","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Tatiana Likhomanenko","raw_affiliation_strings":["Facebook"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102647000","display_name":"Qiantong Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Qiantong Xu","raw_affiliation_strings":["Facebook"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028944337","display_name":"Vineel Pratap","orcid":"https://orcid.org/0000-0003-3333-910X"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Vineel Pratap","raw_affiliation_strings":["Facebook"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027043104","display_name":"Paden Tomasello","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Paden Tomasello","raw_affiliation_strings":["Facebook"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027275703","display_name":"Jacob Kahn","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jacob Kahn","raw_affiliation_strings":["Facebook"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087617906","display_name":"Gilad Avidov","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Gilad Avidov","raw_affiliation_strings":["Facebook"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053915453","display_name":"Ronan Collobert","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ronan Collobert","raw_affiliation_strings":["Facebook"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041907084","display_name":"Gabriel Synnaeve","orcid":"https://orcid.org/0000-0003-1715-3356"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Gabriel Synnaeve","raw_affiliation_strings":["Facebook"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5393,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.85533264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"311","last_page":"315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/computer-science","display_name":"Computer science","score":0.783292829990387},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6973867416381836},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.6895232796669006},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6259489059448242},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5257742404937744},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5076607465744019},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5069947242736816},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4992716312408447},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45411399006843567},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4321076273918152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42072486877441406},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.412424772977829},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3980652391910553},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37698280811309814},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.13019999861717224},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06633025407791138}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.783292829990387},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6973867416381836},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.6895232796669006},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6259489059448242},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5257742404937744},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5076607465744019},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5069947242736816},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4992716312408447},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45411399006843567},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4321076273918152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42072486877441406},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.412424772977829},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3980652391910553},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37698280811309814},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.13019999861717224},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06633025407791138},{"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-1758","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.11745","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.11745","pdf_url":"https://arxiv.org/pdf/2010.11745","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:3093502935","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.11745.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.2010.11745","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.11745","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:2010.11745","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.11745","pdf_url":"https://arxiv.org/pdf/2010.11745","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":[{"id":"https://metadata.un.org/sdg/16","score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3093502935.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W2062164080","https://openalex.org/W2101045344","https://openalex.org/W2115730999","https://openalex.org/W2122028591","https://openalex.org/W2127141656","https://openalex.org/W2134800885","https://openalex.org/W2135479785","https://openalex.org/W2146502635","https://openalex.org/W2193413348","https://openalex.org/W2520160253","https://openalex.org/W2593116425","https://openalex.org/W2680270903","https://openalex.org/W2696967604","https://openalex.org/W2782451907","https://openalex.org/W2786234940","https://openalex.org/W2786459654","https://openalex.org/W2806982421","https://openalex.org/W2884797218","https://openalex.org/W2889282842","https://openalex.org/W2900212944","https://openalex.org/W2901243971","https://openalex.org/W2936774411","https://openalex.org/W2953190524","https://openalex.org/W2963303951","https://openalex.org/W2963399332","https://openalex.org/W2963403868","https://openalex.org/W2963631907","https://openalex.org/W2991213871","https://openalex.org/W2996159613","https://openalex.org/W3015191643","https://openalex.org/W3015726069","https://openalex.org/W3016400019","https://openalex.org/W3018441253","https://openalex.org/W3025165719","https://openalex.org/W3030437843","https://openalex.org/W3032816972","https://openalex.org/W3101648800","https://openalex.org/W3106426924","https://openalex.org/W3131736947"],"related_works":["https://openalex.org/W3198270883","https://openalex.org/W1494198834","https://openalex.org/W2936774411","https://openalex.org/W3099782249","https://openalex.org/W2995181338","https://openalex.org/W2127141656","https://openalex.org/W1524333225","https://openalex.org/W3101648800","https://openalex.org/W3093579165","https://openalex.org/W3030437843","https://openalex.org/W2973049979","https://openalex.org/W2963403868","https://openalex.org/W2125336414","https://openalex.org/W2963818726","https://openalex.org/W2963537624","https://openalex.org/W3173246785","https://openalex.org/W3193697390","https://openalex.org/W3185447076","https://openalex.org/W2886245013","https://openalex.org/W2961301154"],"abstract_inverted_index":{"Is":[0],"pushing":[1],"numbers":[2],"on":[3,21,23,54,106,119,130],"a":[4,24,55,84,101,115],"single":[5,25,56,116],"benchmark":[6],"valuable":[7],"in":[8,14,43,49,67],"automatic":[9],"speech":[10],"recognition?":[11],"Research":[12],"results":[13],"acoustic":[15,44,117],"modeling":[16,45],"are":[17],"typically":[18],"evaluated":[19],"based":[20],"performance":[22,42,76,97,105,129],"dataset.":[26],"While":[27],"the":[28,120],"research":[29,132],"community":[30],"has":[31],"coalesced":[32],"around":[33],"various":[34],"benchmarks,":[35],"we":[36,80,111],"set":[37,87],"out":[38],"to":[39,59],"understand":[40],"generalization":[41,75],"across":[46,77],"datasets":[47,123],"-":[48,124,126],"particular,":[50],"if":[51],"models":[52],"trained":[53],"dataset":[57],"transfer":[58],"other":[60],"(possibly":[61],"out-of-domain)":[62],"datasets.":[63],"We":[64],"show":[65,112],"that,":[66],"general,":[68],"reverberative":[69],"and":[70,133],"additive":[71],"noise":[72],"augmentation":[73],"improves":[74],"domains.":[78],"Further,":[79],"demonstrate":[81],"that":[82,113],"when":[83],"large":[85],"enough":[86],"of":[88],"benchmarks":[89],"is":[90],"used,":[91],"average":[92],"word":[93],"error":[94],"rate":[95],"(WER)":[96],"over":[98],"them":[99],"provides":[100],"good":[102],"proxy":[103],"for":[104],"real-world":[107,134],"noisy":[108],"data.":[109],"Finally,":[110],"training":[114],"model":[118],"most":[121],"widely-used":[122],"combined":[125],"reaches":[127],"competitive":[128],"both":[131],"benchmarks.":[135]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}