{"id":"https://openalex.org/W3139918052","doi":"https://doi.org/10.48550/arxiv.2104.02133","title":"SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network","display_name":"SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network","publication_year":2021,"publication_date":"2021-04-05","ids":{"openalex":"https://openalex.org/W3139918052","doi":"https://doi.org/10.48550/arxiv.2104.02133","mag":"3139918052"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2104.02133","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.02133","pdf_url":"https://arxiv.org/pdf/2104.02133","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.02133","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102811560","display_name":"William Chan","orcid":"https://orcid.org/0000-0001-6205-255X","observed_orcids":["https://orcid.org/0000-0001-6205-255X"]},"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":"Chan, William","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100613715","display_name":"Daniel Park","orcid":"https://orcid.org/0000-0002-1919-0460","observed_orcids":["https://orcid.org/0000-0002-1919-0460"]},"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":"Park, Daniel","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088987351","display_name":"Chris A. Lee","orcid":null,"observed_orcids":[]},"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":"Lee, Chris","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":null,"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","observed_orcids":["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":"Zhang, Yu","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088551093","display_name":"Quoc Viet Le","orcid":"https://orcid.org/0000-0002-1087-2844","observed_orcids":["https://orcid.org/0000-0002-1087-2844"]},"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":"Le, Quoc","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103947107","display_name":"Mohammad Norouzi","orcid":null,"observed_orcids":[]},"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":"Norouzi, Mohammad","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":null,"affiliations":[{"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":false,"cited_by_count":72,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10860","display_name":"Speech and Audio Processing","score":9.999999747378752e-05,"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/T12031","display_name":"Speech and dialogue systems","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.8109999895095825},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.6140000224113464},{"id":"https://openalex.org/keywords/low-resource-speech","display_name":"low-resource speech","score":0.5730000138282776},{"id":"https://openalex.org/keywords/noisy-speech","display_name":"noisy speech","score":0.7979999780654907},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"word error rate","score":0.7379999756813049}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6768032908439636},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6516400575637817},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6131591796875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30703285336494446}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2104.02133","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.02133","pdf_url":"https://arxiv.org/pdf/2104.02133","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2104.02133","doi":"https://doi.org/10.48550/arxiv.2104.02133","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.02133","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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:2104.02133","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.02133","pdf_url":"https://arxiv.org/pdf/2104.02133","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.44999998807907104}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W1978660892","https://openalex.org/W2102113734","https://openalex.org/W2108677974","https://openalex.org/W2123798005","https://openalex.org/W2125336414","https://openalex.org/W2155541015","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2168231600","https://openalex.org/W2194775991","https://openalex.org/W2250357346","https://openalex.org/W2327501763","https://openalex.org/W2530876040","https://openalex.org/W2626778328","https://openalex.org/W2775304348","https://openalex.org/W2799473636","https://openalex.org/W2804935296","https://openalex.org/W2886246524","https://openalex.org/W2889282842","https://openalex.org/W2900212944","https://openalex.org/W2936774411","https://openalex.org/W2939690918","https://openalex.org/W2939710050","https://openalex.org/W2962911098","https://openalex.org/W2963341956","https://openalex.org/W2963742216","https://openalex.org/W2964002616","https://openalex.org/W2991213871","https://openalex.org/W2995181338","https://openalex.org/W2996603747","https://openalex.org/W3001279689","https://openalex.org/W3015146382","https://openalex.org/W3015726069","https://openalex.org/W3015995734","https://openalex.org/W3018441253","https://openalex.org/W3020336359","https://openalex.org/W3026041220","https://openalex.org/W3030437843","https://openalex.org/W3035445001","https://openalex.org/W3036601975","https://openalex.org/W3093502935","https://openalex.org/W3093579165","https://openalex.org/W3094841848","https://openalex.org/W3097777922","https://openalex.org/W3098903812","https://openalex.org/W3099782249","https://openalex.org/W3100859887","https://openalex.org/W3131505732","https://openalex.org/W3131736947","https://openalex.org/W3147962056","https://openalex.org/W3149390355"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829"],"abstract_inverted_index":{"We":[0,98,108,119],"present":[1],"SpeechStew,":[2],"a":[3,11,57,112,124,133,138],"speech":[4,17,116],"recognition":[5,18],"model":[6],"that":[7,101],"is":[8],"trained":[9],"on":[10,74,78,82,86,111],"combination":[12],"of":[13,36,46,59,64],"various":[14],"publicly":[15],"available":[16],"datasets:":[19],"AMI,":[20],"Broadcast":[21],"News,":[22],"Common":[23],"Voice,":[24],"LibriSpeech,":[25],"Switchboard/Fisher,":[26],"Tedlium,":[27],"and":[28,84],"Wall":[29],"Street":[30],"Journal.":[31],"SpeechStew":[32,49,102,110],"simply":[33],"mixes":[34],"all":[35],"these":[37],"datasets":[38],"together,":[39],"without":[40,61,123],"any":[41],"special":[42],"re-weighting":[43],"or":[44,52],"re-balancing":[45],"the":[47,62],"datasets.":[48],"achieves":[50],"SoTA":[51,54],"near":[53],"results":[55,70],"across":[56],"variety":[58],"tasks,":[60],"use":[63],"an":[65],"external":[66,95],"language":[67,96,125,139],"model.":[68,140],"Our":[69],"include":[71],"9.0\\%":[72],"WER":[73,77,81,122,131],"AMI-IHM,":[75],"4.7\\%":[76],"Switchboard,":[79],"8.3\\%":[80],"CallHome,":[83],"1.3\\%":[85],"WSJ,":[87],"which":[88,127],"significantly":[89],"outperforms":[90],"prior":[91],"work":[92],"with":[93,137],"strong":[94,134],"models.":[97],"also":[99],"demonstrate":[100],"learns":[103],"powerful":[104],"transfer":[105],"learning":[106],"representations.":[107],"fine-tune":[109],"noisy":[113],"low":[114],"resource":[115],"dataset,":[117],"CHiME-6.":[118],"achieve":[120],"38.9\\%":[121],"model,":[126],"compares":[128],"to":[129,132],"38.6\\%":[130],"HMM":[135],"baseline":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":29},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":15}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2021-04-13T00:00:00"}