{"id":"https://openalex.org/W3097777922","doi":"https://doi.org/10.21437/interspeech.2020-3015","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","display_name":"Conformer: Convolution-augmented Transformer for Speech Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3097777922","doi":"https://doi.org/10.21437/interspeech.2020-3015","mag":"3097777922"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-3015","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5070108948","display_name":"Anmol Gulati","orcid":"https://orcid.org/0009-0007-2077-9583"},"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":"Anmol Gulati","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048771433","display_name":"James Qin","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":"James Qin","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027763497","display_name":"Chung\u2010Cheng Chiu","orcid":"https://orcid.org/0000-0001-9729-4778"},"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":"Chung-Cheng Chiu","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005777963","display_name":"Niki Parmar","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":"Niki Parmar","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","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 Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001205723","display_name":"Jiahui Yu","orcid":"https://orcid.org/0000-0003-1314-2481"},"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":"Jiahui Yu","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100750907","display_name":"Wei Han","orcid":"https://orcid.org/0000-0002-4201-9645"},"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":"Wei Han","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100738089","display_name":"Shibo Wang","orcid":"https://orcid.org/0000-0001-6621-1722"},"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":"Shibo Wang","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100612731","display_name":"Zhengdong Zhang","orcid":"https://orcid.org/0000-0001-8754-3822"},"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":"Zhengdong Zhang","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","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 Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112901893","display_name":"Ruoming Pang","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":"Ruoming Pang","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5070108948"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":183.8623,"has_fulltext":false,"cited_by_count":2714,"citation_normalized_percentile":{"value":0.99986234,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5036","last_page":"5040"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.996399998664856,"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":0.9954000115394592,"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/transformer","display_name":"Transformer","score":0.6713411808013916},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6417247653007507},{"id":"https://openalex.org/keywords/overlap\u2013add-method","display_name":"Overlap\u2013add method","score":0.5696628093719482},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5619367957115173},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.49672800302505493},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32805564999580383},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3242719769477844},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15122437477111816},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.14198040962219238},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.1153552234172821},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10395938158035278},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08304670453071594},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.057966768741607666}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6713411808013916},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6417247653007507},{"id":"https://openalex.org/C181002996","wikidata":"https://www.wikidata.org/wiki/Q1611641","display_name":"Overlap\u2013add method","level":5,"score":0.5696628093719482},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5619367957115173},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.49672800302505493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32805564999580383},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3242719769477844},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15122437477111816},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.14198040962219238},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.1153552234172821},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10395938158035278},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08304670453071594},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.057966768741607666},{"id":"https://openalex.org/C76563020","wikidata":"https://www.wikidata.org/wiki/Q4817582","display_name":"Fractional Fourier transform","level":4,"score":0.0},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-3015","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W1964175594","https://openalex.org/W1995562189","https://openalex.org/W2095705004","https://openalex.org/W2112739286","https://openalex.org/W2567070169","https://openalex.org/W2892009249","https://openalex.org/W2899423466","https://openalex.org/W2928941594","https://openalex.org/W2936774411","https://openalex.org/W2948981900","https://openalex.org/W2952809536","https://openalex.org/W2962760690","https://openalex.org/W2963414781","https://openalex.org/W2963542740","https://openalex.org/W2964110616","https://openalex.org/W2972818416","https://openalex.org/W2973215447","https://openalex.org/W2979636403","https://openalex.org/W2981413347","https://openalex.org/W2981857663","https://openalex.org/W3015194534","https://openalex.org/W3015537910","https://openalex.org/W3015995734","https://openalex.org/W3016010032","https://openalex.org/W3095173472","https://openalex.org/W4287812455","https://openalex.org/W4295253143","https://openalex.org/W4309845474","https://openalex.org/W4320930577","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4372260258","https://openalex.org/W2267589039","https://openalex.org/W2369791303","https://openalex.org/W2759540840","https://openalex.org/W2133280289","https://openalex.org/W2360069155","https://openalex.org/W2169963286","https://openalex.org/W2919798019","https://openalex.org/W2293685972","https://openalex.org/W2361284596"],"abstract_inverted_index":{"Recently":[0],"Transformer":[1,87],"and":[2,54,60,88,110],"Convolution":[3],"neural":[4,20,52],"network":[5],"(CNN)":[6],"based":[7,90],"models":[8,23,91],"have":[9],"shown":[10],"promising":[11],"results":[12],"in":[13,67],"Automatic":[14],"Speech":[15],"Recognition":[16],"(ASR),":[17],"outperforming":[18],"Recurrent":[19],"networks":[21,53],"(RNNs).Transformer":[22],"are":[24],"good":[25],"at":[26],"capturing":[27],"content-based":[28],"global":[29,61],"interactions,":[30],"while":[31],"CNNs":[32],"exploit":[33],"local":[34,59],"features":[35],"effectively.In":[36],"this":[37,71],"work,":[38],"we":[39,73],"achieve":[40],"the":[41,75,85,95],"best":[42],"of":[43,63,104,122,127],"both":[44,58],"worlds":[45],"by":[46],"studying":[47],"how":[48],"to":[49,56],"combine":[50],"convolution":[51],"transformers":[55],"model":[57,101,109,115,126],"dependencies":[62],"an":[64,112],"audio":[65],"sequence":[66],"a":[68,107,124],"parameter-efficient":[69],"way.To":[70],"regard,":[72],"propose":[74],"convolution-augmented":[76],"transformer":[77],"for":[78],"speech":[79],"recognition,":[80],"named":[81],"Conformer.Conformer":[82],"significantly":[83],"outperforms":[84],"previous":[86],"CNN":[89],"achieving":[92],"state-of-the-art":[93],"accuracies.On":[94],"widely":[96],"used":[97],"LibriSpeech":[98],"benchmark,":[99],"our":[100],"achieves":[102],"WER":[103],"2.1%/4.3%without":[105],"using":[106],"language":[108,114],"1.9%/3.9%with":[111],"external":[113],"on":[116],"test/testother.We":[117],"also":[118],"observe":[119],"competitive":[120],"performance":[121],"2.7%/6.3%with":[123],"small":[125],"only":[128],"10M":[129],"parameters.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":145},{"year":2025,"cited_by_count":609},{"year":2024,"cited_by_count":608},{"year":2023,"cited_by_count":696},{"year":2022,"cited_by_count":424},{"year":2021,"cited_by_count":223},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":1}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}