{"id":"https://openalex.org/W3016010032","doi":"https://doi.org/10.1109/icassp40776.2020.9053896","title":"Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss","display_name":"Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016010032","doi":"https://doi.org/10.1109/icassp40776.2020.9053896","mag":"3016010032"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053896","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/A5115603610","display_name":"Qian Zhang","orcid":"https://orcid.org/0000-0001-5975-9781"},"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":"Qian Zhang","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/A5086894713","display_name":"Lu Han","orcid":"https://orcid.org/0000-0002-1120-3220"},"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":"Han Lu","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/A5108537573","display_name":"Ha\u015fim Sak","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":"Hasim Sak","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/A5101403998","display_name":"Anshuman Tripathi","orcid":"https://orcid.org/0000-0002-4902-3719"},"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":"Anshuman Tripathi","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/A5030109648","display_name":"Erik McDermott","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":"Erik McDermott","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/A5075555533","display_name":"Stephen Koo","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":"Stephen Koo","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/A5101051347","display_name":"Shankar Kumar","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":"Shankar Kumar","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":7,"corresponding_author_ids":["https://openalex.org/A5115603610"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":44.7175,"has_fulltext":false,"cited_by_count":446,"citation_normalized_percentile":{"value":0.99879015,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7829","last_page":"7833"},"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":0.9997000098228455,"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":0.9991000294685364,"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/encoder","display_name":"Encoder","score":0.7232558131217957},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7183559536933899},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6687674522399902},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6664003133773804},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6634507179260254},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6608359217643738},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4299502968788147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39874500036239624},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2666018605232239},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24500861763954163},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11767438054084778},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08356553316116333}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7232558131217957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7183559536933899},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6687674522399902},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6664003133773804},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6634507179260254},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6608359217643738},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4299502968788147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39874500036239624},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2666018605232239},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24500861763954163},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11767438054084778},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08356553316116333},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053896","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":"Peace, Justice and strong institutions","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1560013842","https://openalex.org/W1828163288","https://openalex.org/W2108677974","https://openalex.org/W2127141656","https://openalex.org/W2293634267","https://openalex.org/W2491408735","https://openalex.org/W2577366047","https://openalex.org/W2746192915","https://openalex.org/W2798657914","https://openalex.org/W2802023636","https://openalex.org/W2892009249","https://openalex.org/W2913718171","https://openalex.org/W2936774411","https://openalex.org/W2941814890","https://openalex.org/W2943845043","https://openalex.org/W2962707338","https://openalex.org/W2963403868","https://openalex.org/W2963414781","https://openalex.org/W2963542740","https://openalex.org/W2964089206","https://openalex.org/W2964110616","https://openalex.org/W2972451902","https://openalex.org/W2981696585","https://openalex.org/W2981857663","https://openalex.org/W3008174054","https://openalex.org/W4385245566","https://openalex.org/W6629717138","https://openalex.org/W6638749077","https://openalex.org/W6676315081","https://openalex.org/W6696934422","https://openalex.org/W6723310180","https://openalex.org/W6739901393","https://openalex.org/W6754299077","https://openalex.org/W6761563299","https://openalex.org/W6769557084","https://openalex.org/W6769647859"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W2025614924","https://openalex.org/W2735765216","https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3145575561","https://openalex.org/W2995886640","https://openalex.org/W2221419418"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,161],"present":[4,106],"an":[5],"end-to-end":[6],"speech":[7,20],"recognition":[8,21],"model":[9,94,147,175],"with":[10,49,97,130],"Transformer":[11,23,91,122],"encoders":[12,46],"that":[13,113,140,160],"can":[14,162],"be":[15],"used":[16,30],"in":[17,120,135],"a":[18,50,55,132,179],"streaming":[19,103],"system.":[22],"computation":[24],"blocks":[25],"based":[26],"on":[27,108,152],"self-attention":[28,119],"are":[29,47],"to":[31,53,75,102,178],"encode":[32],"both":[33,42],"audio":[34,43],"and":[35,44,69,169],"label":[36,45,60,70],"sequences":[37],"independently.":[38],"The":[39,93],"activations":[40],"from":[41],"combined":[48],"feed-forward":[51],"layer":[52],"compute":[54],"probability":[56],"distribution":[57],"over":[58],"the":[59,76,98,109,115,121,141,153,164],"space":[61],"for":[62,86,118,128],"every":[63],"combination":[64],"of":[65,90,145,173,182],"acoustic":[66],"frame":[67],"position":[68],"history.":[71],"This":[72],"is":[73,95],"similar":[74],"Recurrent":[77],"Neural":[78],"Network":[79],"Transducer":[80],"(RNN-T)":[81],"model,":[82],"which":[83],"uses":[84],"RNNs":[85],"information":[87],"encoding":[88],"instead":[89],"encoders.":[92],"trained":[96],"RNN-T":[99],"loss":[100],"well-suited":[101],"decoding.":[104],"We":[105,137],"results":[107,157],"LibriSpeech":[110,154],"dataset":[111],"showing":[112],"limiting":[114],"left":[116],"context":[117],"layers":[123],"makes":[124],"decoding":[125],"computationally":[126],"tractable":[127],"streaming,":[129],"only":[131],"slight":[133],"degradation":[134],"accuracy.":[136],"also":[138,158],"show":[139,159],"full":[142,167],"attention":[143,168,171],"version":[144],"our":[146,174],"beats":[148],"the-state-of-the":[149],"art":[150],"accuracy":[151],"benchmarks.":[155],"Our":[156],"bridge":[163],"gap":[165],"between":[166],"limited":[170,180],"versions":[172],"by":[176],"attending":[177],"number":[181],"future":[183],"frames.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":44},{"year":2024,"cited_by_count":66},{"year":2023,"cited_by_count":94},{"year":2022,"cited_by_count":69},{"year":2021,"cited_by_count":114},{"year":2020,"cited_by_count":52},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}