{"id":"https://openalex.org/W3001899777","doi":"https://doi.org/10.21437/interspeech.2020-2840","title":"Scaling Up Online Speech Recognition Using ConvNets","display_name":"Scaling Up Online Speech Recognition Using ConvNets","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3001899777","doi":"https://doi.org/10.21437/interspeech.2020-2840","mag":"3001899777"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2840","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2840","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.09727","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":["Meta (Israel), Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","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":["Meta (Israel), Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","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":["Meta (Israel), Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","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":["Meta (Israel), Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","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":["Meta (Israel), Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087325198","display_name":"Awni Hannun","orcid":"https://orcid.org/0000-0003-3080-4002"},"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":"Awni Hannun","raw_affiliation_strings":["Meta (Israel), Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025751434","display_name":"Vitaliy Liptchinsky","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":"Vitaliy Liptchinsky","raw_affiliation_strings":["Meta (Israel), Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","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":["Meta (Israel), Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","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":["Meta (Israel), Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7603,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.87797044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3376","last_page":"3380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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":0.8144445419311523},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.765243649482727},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6332122683525085},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6228227615356445},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6073511838912964},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48139050602912903},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4326012432575226},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4271355867385864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3810780644416809},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3651166260242462},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.32055580615997314},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07304912805557251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8144445419311523},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.765243649482727},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6332122683525085},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6228227615356445},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6073511838912964},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48139050602912903},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4326012432575226},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4271355867385864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3810780644416809},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3651166260242462},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.32055580615997314},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07304912805557251},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-2840","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2840","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"},{"id":"pmh:oai:arXiv.org:2001.09727","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.09727","pdf_url":"https://arxiv.org/pdf/2001.09727","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:3001899777","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2001.09727.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.2001.09727","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.09727","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:2001.09727","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.09727","pdf_url":"https://arxiv.org/pdf/2001.09727","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":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3001899777.pdf","grobid_xml":"https://content.openalex.org/works/W3001899777.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W2193413348","https://openalex.org/W2514741789","https://openalex.org/W2531409750","https://openalex.org/W2612445135","https://openalex.org/W2631415506","https://openalex.org/W2729190387","https://openalex.org/W2799800213","https://openalex.org/W2892090442","https://openalex.org/W2904818793","https://openalex.org/W2936774411","https://openalex.org/W2953190524","https://openalex.org/W2953333557","https://openalex.org/W2962760690","https://openalex.org/W2963403868","https://openalex.org/W2963979492","https://openalex.org/W2964084166","https://openalex.org/W2964307104","https://openalex.org/W2972818416","https://openalex.org/W2975381464","https://openalex.org/W2979286696","https://openalex.org/W2981581604","https://openalex.org/W2981857663","https://openalex.org/W2987019345","https://openalex.org/W2991213871","https://openalex.org/W3037932933","https://openalex.org/W3127686677"],"related_works":["https://openalex.org/W3096104971","https://openalex.org/W2936774411","https://openalex.org/W2327501763","https://openalex.org/W1494198834","https://openalex.org/W2981857663","https://openalex.org/W2407080277","https://openalex.org/W5111544","https://openalex.org/W2809840276","https://openalex.org/W3197304116","https://openalex.org/W2060395796","https://openalex.org/W2785712565","https://openalex.org/W3109079702","https://openalex.org/W2949229618","https://openalex.org/W3148986242","https://openalex.org/W3162899666","https://openalex.org/W2472414238","https://openalex.org/W3017216675","https://openalex.org/W2775304348","https://openalex.org/W3027637851","https://openalex.org/W2939518062"],"abstract_inverted_index":{"We":[0,19],"design":[1,86],"an":[2],"online":[3],"end-to-end":[4],"speech":[5],"recognition":[6],"system":[7,40],"based":[8,101],"on":[9,102],"Time-Depth":[10],"Separable":[11],"(TDS)":[12],"convolutions":[13],"and":[14,32,59,93],"Connectionist":[15],"Temporal":[16],"Classification":[17],"(CTC).":[18],"improve":[20],"the":[21,29,45,68,71,82,103],"core":[22],"TDS":[23],"architecture":[24],"in":[25],"order":[26],"to":[27,67],"limit":[28],"future":[30],"context":[31],"hence":[33],"reduce":[34],"latency":[35,58],"while":[36,54],"maintaining":[37],"accuracy.":[38],"The":[39],"has":[41],"almost":[42],"three":[43],"times":[44],"throughput":[46],"of":[47,70,84],"a":[48,60],"well":[49],"tuned":[50,100],"hybrid":[51],"ASR":[52],"baseline":[53],"also":[55],"having":[56],"lower":[57],"better":[61],"word":[62],"error":[63],"rate.":[64],"Also":[65],"important":[66],"efficiency":[69],"recognizer":[72],"is":[73],"our":[74,85],"highly":[75],"optimized":[76],"beam":[77],"search":[78],"decoder.":[79],"To":[80],"show":[81],"impact":[83],"choices,":[87],"we":[88],"analyze":[89],"throughput,":[90],"latency,":[91],"accuracy,":[92],"discuss":[94],"how":[95],"these":[96],"metrics":[97],"can":[98],"be":[99],"user":[104],"requirements.":[105]},"counts_by_year":[{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}