{"id":"https://openalex.org/W3011339933","doi":"https://doi.org/10.1109/icassp40776.2020.9053606","title":"Deliberation Model Based Two-Pass End-To-End Speech Recognition","display_name":"Deliberation Model Based Two-Pass End-To-End Speech Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3011339933","doi":"https://doi.org/10.1109/icassp40776.2020.9053606","mag":"3011339933"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053606","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/A5029338576","display_name":"Ke Hu","orcid":"https://orcid.org/0000-0002-1599-1519"},"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":"Ke Hu","raw_affiliation_strings":["Google, Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., 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, Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., 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, Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032640894","display_name":"Rohit Prabhavalkar","orcid":"https://orcid.org/0000-0001-5331-6058"},"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":"Rohit Prabhavalkar","raw_affiliation_strings":["Google, Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5029338576"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":8.1401,"has_fulltext":false,"cited_by_count":75,"citation_normalized_percentile":{"value":0.97990817,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7799","last_page":"7803"},"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9991000294685364,"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":0.7822829484939575},{"id":"https://openalex.org/keywords/deliberation","display_name":"Deliberation","score":0.6157785058021545},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5944921374320984},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5884882211685181},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5706332325935364},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5521324872970581},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5224253535270691},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5077806115150452},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4901672303676605},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4802875220775604},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4745427072048187},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.436581015586853},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42083364725112915},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.41199174523353577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36093854904174805},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.35587042570114136},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22282922267913818},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10448801517486572}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7822829484939575},{"id":"https://openalex.org/C2776946740","wikidata":"https://www.wikidata.org/wiki/Q358652","display_name":"Deliberation","level":3,"score":0.6157785058021545},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5944921374320984},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5884882211685181},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5706332325935364},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5521324872970581},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5224253535270691},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5077806115150452},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4901672303676605},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4802875220775604},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4745427072048187},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.436581015586853},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42083364725112915},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.41199174523353577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36093854904174805},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35587042570114136},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22282922267913818},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10448801517486572},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053606","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W2064675550","https://openalex.org/W2121879602","https://openalex.org/W2213952365","https://openalex.org/W2327501763","https://openalex.org/W2402144811","https://openalex.org/W2515439472","https://openalex.org/W2526425061","https://openalex.org/W2617258110","https://openalex.org/W2752047430","https://openalex.org/W2794365787","https://openalex.org/W2916997151","https://openalex.org/W2924677654","https://openalex.org/W2928941594","https://openalex.org/W2938973646","https://openalex.org/W2944255943","https://openalex.org/W2953384591","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963122170","https://openalex.org/W2963240019","https://openalex.org/W2963403868","https://openalex.org/W2963414781","https://openalex.org/W2963747784","https://openalex.org/W2963782041","https://openalex.org/W2964138484","https://openalex.org/W2972650231","https://openalex.org/W2972880214","https://openalex.org/W2973122799","https://openalex.org/W3008181812","https://openalex.org/W3103005696","https://openalex.org/W4294619240","https://openalex.org/W4385245566","https://openalex.org/W6638749077","https://openalex.org/W6688428952","https://openalex.org/W6713134421","https://openalex.org/W6728030952","https://openalex.org/W6739901393","https://openalex.org/W6743726175","https://openalex.org/W6749740488","https://openalex.org/W6760633627","https://openalex.org/W6843673214"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W2753773138","https://openalex.org/W1732468982","https://openalex.org/W1761388607","https://openalex.org/W3204354834","https://openalex.org/W1997922073","https://openalex.org/W6292469","https://openalex.org/W2916997151","https://openalex.org/W2949174760"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"models":[2,64],"have":[3],"made":[4],"rapid":[5],"progress":[6],"in":[7,113,164],"automatic":[8],"speech":[9],"recognition":[10],"(ASR)":[11],"and":[12,39,81,119,159],"perform":[13],"competitively":[14],"relative":[15,106],"to":[16,30,51,53,58,76,78,93,110,129],"conventional":[17,132],"models.":[18],"To":[19],"further":[20],"improve":[21],"the":[22,35,148,156],"quality,":[23],"a":[24,45,59,85,123,130,152],"two-pass":[25],"model":[26,42,49,103,136],"has":[27,151],"been":[28],"proposed":[29,101],"rescore":[31,54],"streamed":[32],"hypotheses":[33,83],"using":[34,84],"non-streaming":[36],"Listen,":[37],"Attend":[38],"Spell":[40],"(LAS)":[41],"while":[43],"maintaining":[44],"reasonable":[46],"latency.":[47],"The":[48,100],"attends":[50],"acoustics":[52,80],"hypotheses,":[55],"as":[56],"opposed":[57],"class":[60],"of":[61,145],"neural":[62],"correction":[63],"that":[65],"use":[66],"only":[67],"first-pass":[68,82,98],"text":[69],"hypotheses.":[70,99],"In":[71,143],"this":[72],"work,":[73],"we":[74],"propose":[75],"attend":[77],"both":[79],"deliberation":[86,102,149],"network.":[87],"A":[88],"bidirectional":[89],"encoder":[90],"is":[91],"used":[92],"extract":[94],"context":[95],"information":[96],"from":[97],"achieves":[104],"12%":[105],"WER":[107],"reduction":[108,121],"compared":[109],"LAS":[111,157],"rescoring":[112],"Google":[114],"Voice":[115],"Search":[116],"(VS)":[117],"tasks,":[118],"23%":[120],"on":[122],"proper":[124],"noun":[125],"test":[126],"set.":[127],"Compared":[128],"large":[131],"model,":[133],"our":[134],"best":[135],"performs":[137],"21%":[138],"relatively":[139],"better":[140],"for":[141],"VS.":[142],"terms":[144],"computational":[146],"complexity,":[147],"decoder":[150],"larger":[153],"size":[154],"than":[155],"decoder,":[158],"hence":[160],"requires":[161],"more":[162],"computations":[163],"second-pass":[165],"decoding.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":6}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}