{"id":"https://openalex.org/W3157428800","doi":"https://doi.org/10.21437/interspeech.2021-211","title":"On the Limit of English Conversational Speech Recognition","display_name":"On the Limit of English Conversational Speech Recognition","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3157428800","doi":"https://doi.org/10.21437/interspeech.2021-211","mag":"3157428800"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-211","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-211","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.00982","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047353872","display_name":"Zolt\u00e1n T\u00fcske","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zolt\u00e1n T\u00fcske","raw_affiliation_strings":["IBM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM (United States), Armonk, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM (United States), Armonk, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2062","last_page":"2066"},"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":0.9991999864578247,"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":0.9986000061035156,"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/benchmark","display_name":"Benchmark (surveying)","score":0.834099531173706},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7465829253196716},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7147598266601562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7116459608078003},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6696083545684814},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.6544557213783264},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6172517538070679},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4439650774002075},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.44073158502578735},{"id":"https://openalex.org/keywords/compensation","display_name":"Compensation (psychology)","score":0.433171808719635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3422528803348541},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19998154044151306},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1389038860797882},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12290409207344055}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.834099531173706},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7465829253196716},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7147598266601562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7116459608078003},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6696083545684814},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.6544557213783264},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6172517538070679},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4439650774002075},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.44073158502578735},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.433171808719635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3422528803348541},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19998154044151306},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1389038860797882},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12290409207344055},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-211","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-211","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:2105.00982","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.00982","pdf_url":"https://arxiv.org/pdf/2105.00982","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:3157428800","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2105.00982.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.2105.00982","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2105.00982","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.00982","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.00982","pdf_url":"https://arxiv.org/pdf/2105.00982","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":0.4099999964237213,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3157428800.pdf","grobid_xml":"https://content.openalex.org/works/W3157428800.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W144554552","https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W1904365287","https://openalex.org/W1915251500","https://openalex.org/W1989674786","https://openalex.org/W2009150118","https://openalex.org/W2064675550","https://openalex.org/W2079623482","https://openalex.org/W2090861223","https://openalex.org/W2097316030","https://openalex.org/W2144513243","https://openalex.org/W2145249131","https://openalex.org/W2158275940","https://openalex.org/W2183341477","https://openalex.org/W2193413348","https://openalex.org/W2296073425","https://openalex.org/W2327501763","https://openalex.org/W2404463488","https://openalex.org/W2407080277","https://openalex.org/W2577366047","https://openalex.org/W2622263826","https://openalex.org/W2782451907","https://openalex.org/W2799958557","https://openalex.org/W2802023636","https://openalex.org/W2888781539","https://openalex.org/W2892009249","https://openalex.org/W2908510526","https://openalex.org/W2916979304","https://openalex.org/W2936774411","https://openalex.org/W2937780860","https://openalex.org/W2962970071","https://openalex.org/W2963088785","https://openalex.org/W2963260202","https://openalex.org/W2963266252","https://openalex.org/W2963403868","https://openalex.org/W2963669405","https://openalex.org/W2964089206","https://openalex.org/W2964110616","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W2972692349","https://openalex.org/W3002595344","https://openalex.org/W3008037978","https://openalex.org/W3015823121","https://openalex.org/W3016010032","https://openalex.org/W3097777922","https://openalex.org/W3097964672","https://openalex.org/W3136989387","https://openalex.org/W3163300396"],"related_works":["https://openalex.org/W3198654230","https://openalex.org/W3002595344","https://openalex.org/W3097747488","https://openalex.org/W2799800213","https://openalex.org/W2936078256","https://openalex.org/W2898132662","https://openalex.org/W3008870153","https://openalex.org/W3016155933","https://openalex.org/W3007528493","https://openalex.org/W2069483556","https://openalex.org/W2537374808","https://openalex.org/W2057950125","https://openalex.org/W2153338568","https://openalex.org/W2949079381","https://openalex.org/W2153295945","https://openalex.org/W2981762175","https://openalex.org/W2972677740","https://openalex.org/W2095033330","https://openalex.org/W3015559362","https://openalex.org/W2405622356"],"abstract_inverted_index":{"In":[0,23],"our":[1,56],"previous":[2],"work":[3],"we":[4,26,50,84],"demonstrated":[5],"that":[6],"a":[7,137,158],"single":[8],"headed":[9],"attention":[10],"encoder-decoder":[11],"model":[12,68],"is":[13,164],"able":[14],"to":[15,124],"reach":[16],"state-of-the-art":[17],"results":[18,30],"in":[19],"conversational":[20],"speech":[21,48],"recognition.":[22],"this":[24],"paper,":[25],"further":[27],"improve":[28],"the":[29,52,66,70,91,107,119,125,162,168,171],"for":[31],"both":[32],"Switchboard":[33],"300":[34],"and":[35,46,83,87,93,111,130,143,148,157],"2000.":[36],"Through":[37],"use":[38],"of":[39,55,65,78,96,161,170],"an":[40,79,133],"improved":[41,134],"optimizer,":[42],"speaker":[43],"vector":[44],"embeddings,":[45],"alternative":[47],"representations":[49],"reduce":[51],"recognition":[53],"errors":[54],"LSTM":[57,101],"system":[58],"on":[59,90,140,146,155],"Switchboard-300":[60],"by":[61],"4%":[62],"relative.":[63],"Compensation":[64],"decoder":[67],"with":[69,98,132],"probability":[71],"ratio":[72],"approach":[73],"allows":[74],"more":[75,112],"efficient":[76],"integration":[77],"external":[80],"language":[81,116],"model,":[82],"report":[85],"5.9%":[86],"11.5%":[88],"WER":[89,145],"SWB":[92,147],"CHM":[94],"parts":[95],"Hub5'00":[97],"very":[99],"simple":[100],"models.":[102,117],"Our":[103,150],"study":[104],"also":[105,153],"considers":[106],"recently":[108],"proposed":[109],"conformer,":[110],"advanced":[113],"self-attention":[114],"based":[115],"Overall,":[118],"conformer":[120],"shows":[121],"similar":[122],"performance":[123],"LSTM;":[126],"nevertheless,":[127],"their":[128],"combination":[129],"decoding":[131],"LM":[135],"reaches":[136],"new":[138,159],"record":[139],"Switchboard-300,":[141],"5.0%":[142],"10.0%":[144],"CHM.":[149],"findings":[151],"are":[152],"confirmed":[154],"Switchboard-2000,":[156],"state":[160],"art":[163],"reported,":[165],"practically":[166],"reaching":[167],"limit":[169],"benchmark.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}