{"id":"https://openalex.org/W3015927303","doi":"https://doi.org/10.1109/icassp40776.2020.9054715","title":"Towards Fast and Accurate Streaming End-To-End ASR","display_name":"Towards Fast and Accurate Streaming End-To-End ASR","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015927303","doi":"https://doi.org/10.1109/icassp40776.2020.9054715","mag":"3015927303"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101706071","display_name":"Bo Li","orcid":"https://orcid.org/0000-0003-3605-9437"},"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":"Bo Li","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001306222","display_name":"Shuo-Yiin Chang","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":"Shuo-yiin Chang","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"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":"Tara N. Sainath","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","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 LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101319167","display_name":"Yanzhang He","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":"Yanzhang He","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032931723","display_name":"Trevor Strohman","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":"Trevor Strohman","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","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 LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101706071"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":13.5208,"has_fulltext":false,"cited_by_count":112,"citation_normalized_percentile":{"value":0.99036027,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6069","last_page":"6073"},"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":0.9983000159263611,"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":0.9951000213623047,"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/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7734240293502808},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7603614330291748},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6807074546813965},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6410752534866333},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6356629729270935},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6331101655960083},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.606724202632904},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5558359622955322},{"id":"https://openalex.org/keywords/percentile","display_name":"Percentile","score":0.5010049343109131},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4409922957420349},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.34702324867248535},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2915706932544708},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10490232706069946},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09954938292503357},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0906355082988739}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7734240293502808},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7603614330291748},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6807074546813965},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6410752534866333},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6356629729270935},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6331101655960083},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.606724202632904},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5558359622955322},{"id":"https://openalex.org/C122048520","wikidata":"https://www.wikidata.org/wiki/Q2913954","display_name":"Percentile","level":2,"score":0.5010049343109131},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4409922957420349},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34702324867248535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2915706932544708},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10490232706069946},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09954938292503357},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0906355082988739},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":38,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W2102113734","https://openalex.org/W2114016253","https://openalex.org/W2131342762","https://openalex.org/W2515439472","https://openalex.org/W2526425061","https://openalex.org/W2577366047","https://openalex.org/W2617258110","https://openalex.org/W2625979394","https://openalex.org/W2742061524","https://openalex.org/W2892300106","https://openalex.org/W2928941594","https://openalex.org/W2935756939","https://openalex.org/W2944255943","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2963122170","https://openalex.org/W2963403868","https://openalex.org/W2963414781","https://openalex.org/W2963747784","https://openalex.org/W2972977747","https://openalex.org/W2973122799","https://openalex.org/W3008284571","https://openalex.org/W3103005696","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6639156005","https://openalex.org/W6675365184","https://openalex.org/W6728030952","https://openalex.org/W6732447497","https://openalex.org/W6739901393","https://openalex.org/W6747398299","https://openalex.org/W6753435171","https://openalex.org/W6760633627","https://openalex.org/W6774019882"],"related_works":["https://openalex.org/W2916997151","https://openalex.org/W2495256954","https://openalex.org/W2259317772","https://openalex.org/W2949174760","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W4398173524","https://openalex.org/W4290708361"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"models":[2,9],"fold":[3],"the":[4,78,94,144,148,179],"acoustic,":[5],"pronunciation":[6],"and":[7,63,88,112,133,172],"language":[8],"of":[10,25],"a":[11,21,28,47,120,129],"conventional":[12,29],"speech":[13],"recognition":[14],"model":[15,50,83],"into":[16],"one":[17],"neural":[18,42],"network":[19,43],"with":[20,85,128,163],"much":[22],"smaller":[23],"number":[24],"parameters":[26],"than":[27],"ASR":[30,57],"system,":[31],"thus":[32],"making":[33],"it":[34,139],"suitable":[35],"for":[36,55,158],"on-device":[37,56],"applications.":[38],"For":[39,59],"example,":[40],"recurrent":[41],"transducer":[44],"(RNN-T)":[45],"as":[46],"streaming":[48],"E2E":[49,73],"has":[51],"shown":[52],"promising":[53],"potential":[54],"[1].":[58],"such":[60],"applications,":[61],"quality":[62],"latency":[64,75,115,175],"are":[65],"two":[66],"critical":[67],"factors.":[68],"We":[69,125],"propose":[70],"to":[71,155,178],"reduce":[72],"model's":[74],"by":[76],"extending":[77],"RNN-T":[79,160,182],"endpointer":[80],"(RNN-T":[81],"EP)":[82],"[2]":[84,118,184],"additional":[86],"early":[87],"late":[89],"penalties.":[90],"By":[91],"further":[92],"applying":[93],"minimum":[95],"word":[96,107],"error":[97,108],"rate":[98,109],"(MWER)":[99],"training":[100,165],"technique":[101],"[3],":[102],"we":[103],"achieved":[104],"8.0%":[105],"relative":[106,169],"(WER)":[110],"reduction":[111,116,151,171],"130ms":[113],"90-percentile":[114,174],"over":[117],"on":[119],"Voice":[121],"Search":[122],"test":[123],"set.":[124],"also":[126],"experimented":[127],"second-pass":[130],"Listen,":[131],"Attend":[132],"Spell":[134],"(LAS)":[135],"rescorer":[136],"[4].":[137],"Although":[138],"did":[140],"not":[141],"directly":[142],"improve":[143],"first":[145],"pass":[146],"latency,":[147],"large":[149],"WER":[150,157,170],"provides":[152],"extra":[153],"room":[154],"trade":[156],"latency.":[159],"EP+LAS,":[161],"together":[162],"MWER":[164],"brings":[166],"in":[167],"18.7%":[168],"160ms":[173],"reductions":[176],"compared":[177],"original":[180],"proposed":[181],"EP":[183],"model.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":37},{"year":2020,"cited_by_count":25}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}