{"id":"https://openalex.org/W3095173472","doi":"https://doi.org/10.21437/interspeech.2020-2059","title":"ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context","display_name":"ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095173472","doi":"https://doi.org/10.21437/interspeech.2020-2059","mag":"3095173472"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2059","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2059","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/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":true,"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/A5100612738","display_name":"Zhengdong Zhang","orcid":"https://orcid.org/0000-0003-4671-8184"},"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/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/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/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/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":false,"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/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"]}]},{"author_position":"last","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5100750907"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":21.6229,"has_fulltext":false,"cited_by_count":255,"citation_normalized_percentile":{"value":0.99563831,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3610","last_page":"3614"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9961000084877014,"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/T11309","display_name":"Music and Audio Processing","score":0.9937999844551086,"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":0.8153681755065918},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7291594743728638},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6607367396354675},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5875111818313599},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4231332540512085},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3314379155635834}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8153681755065918},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7291594743728638},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6607367396354675},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5875111818313599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4231332540512085},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3314379155635834},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2059","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2059","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":[{"display_name":"Peace, Justice and strong institutions","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":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/W1836465849","https://openalex.org/W2033256038","https://openalex.org/W2079623482","https://openalex.org/W2112021726","https://openalex.org/W2164240571","https://openalex.org/W2194775991","https://openalex.org/W2288817436","https://openalex.org/W2530876040","https://openalex.org/W2531409750","https://openalex.org/W2898732869","https://openalex.org/W2904818793","https://openalex.org/W2928941594","https://openalex.org/W2936774411","https://openalex.org/W2962760690","https://openalex.org/W2963163009","https://openalex.org/W2963414781","https://openalex.org/W2972818416","https://openalex.org/W2973215447","https://openalex.org/W2981857663","https://openalex.org/W3007904524","https://openalex.org/W3008191852","https://openalex.org/W3015194534","https://openalex.org/W3015537910","https://openalex.org/W3015995734","https://openalex.org/W3016010032","https://openalex.org/W3149629662","https://openalex.org/W4286800115","https://openalex.org/W4309845474","https://openalex.org/W4320930577","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2748454020","https://openalex.org/W3119610945","https://openalex.org/W3181746755","https://openalex.org/W3016958897","https://openalex.org/W4283379348","https://openalex.org/W4312417841","https://openalex.org/W2735477435","https://openalex.org/W3045739591","https://openalex.org/W2807436399","https://openalex.org/W3001728219"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNN)":[3],"have":[4],"shown":[5],"promising":[6],"results":[7],"for":[8],"end-to-end":[9],"speech":[10],"recognition,":[11],"albeit":[12],"still":[13],"behind":[14],"RNN/transformer":[15],"based":[16],"models":[17],"in":[18],"performance.In":[19],"this":[20,27],"paper,":[21],"we":[22,38,59],"study":[23],"how":[24],"to":[25,115],"bridge":[26],"gap":[28],"and":[29,77,103,124],"go":[30],"beyond":[31],"with":[32,101],"a":[33,42,61,89,138],"novel":[34],"CNN-RNN-transducer":[35],"architecture,":[36],"which":[37],"call":[39],"ContextNet.ContextNet":[40],"features":[41],"fully":[43],"convolutional":[44],"encoder":[45],"that":[46,65,71,80],"incorporates":[47],"global":[48],"context":[49],"information":[50],"into":[51],"convolution":[52],"layers":[53],"by":[54],"adding":[55],"squeeze-and-excitation":[56],"modules.In":[57],"addition,":[58],"propose":[60],"simple":[62],"scaling":[63],"method":[64],"scales":[66],"the":[67,82,109,116,130],"widths":[68],"of":[69,94,121,129],"Con-textNet":[70],"achieves":[72,88],"good":[73],"trade-off":[74],"between":[75],"computation":[76],"accuracy.We":[78],"demonstrate":[79],"on":[81,108,137],"widely":[83],"used":[84],"Librispeech":[85],"benchmark,":[86],"ContextNet":[87,132],"word":[90],"error":[91],"rate":[92],"(WER)":[93],"2.1%/4.6%without":[95],"external":[96],"language":[97],"model":[98,120,133],"(LM),":[99],"1.9%/4.1%":[100],"LM":[102,123],"2.9%/7.0%with":[104],"only":[105],"10M":[106],"parameters":[107],"clean/noisy":[110],"LibriSpeech":[111],"test":[112],"sets.This":[113],"compares":[114],"best":[117],"previously":[118],"published":[119],"2.0%/4.6%with":[122],"3.9%/11.3%with":[125],"20M":[126],"parameters.The":[127],"superiority":[128],"proposed":[131],"is":[134],"also":[135],"verified":[136],"much":[139],"larger":[140],"internal":[141],"dataset.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":39},{"year":2024,"cited_by_count":53},{"year":2023,"cited_by_count":58},{"year":2022,"cited_by_count":50},{"year":2021,"cited_by_count":46},{"year":2020,"cited_by_count":5}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}