{"id":"https://openalex.org/W3015686596","doi":"https://doi.org/10.1109/icassp40776.2020.9054419","title":"Rnn-Transducer with Stateless Prediction Network","display_name":"Rnn-Transducer with Stateless Prediction Network","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015686596","doi":"https://doi.org/10.1109/icassp40776.2020.9054419","mag":"3015686596"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054419","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054419","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/A5074978208","display_name":"Mohammadreza Ghodsi","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":true,"raw_author_name":"Mohammadreza Ghodsi","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100359288","display_name":"Xiaofeng Liu","orcid":"https://orcid.org/0000-0002-4514-2016"},"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":"Xiaofeng Liu","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004185134","display_name":"James Apfel","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":"James Apfel","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065949254","display_name":"Rodrigo Cabrera","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":"Rodrigo Cabrera","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058585526","display_name":"Eugene Weinstein","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":"Eugene Weinstein","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5074978208"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":7.8475,"has_fulltext":false,"cited_by_count":95,"citation_normalized_percentile":{"value":0.97919187,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"2020","issue":null,"first_page":"7049","last_page":"7053"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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":0.9980999827384949,"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/overfitting","display_name":"Overfitting","score":0.8896465301513672},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8422760367393494},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6600878238677979},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6374474763870239},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6059917211532593},{"id":"https://openalex.org/keywords/stateless-protocol","display_name":"Stateless protocol","score":0.6043631434440613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.491146057844162},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48417928814888},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4623068571090698},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4168747663497925},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39091718196868896},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.25016874074935913},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1820676326751709}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8896465301513672},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8422760367393494},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6600878238677979},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6374474763870239},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6059917211532593},{"id":"https://openalex.org/C103613024","wikidata":"https://www.wikidata.org/wiki/Q230924","display_name":"Stateless protocol","level":3,"score":0.6043631434440613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.491146057844162},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48417928814888},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4623068571090698},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4168747663497925},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39091718196868896},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25016874074935913},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1820676326751709},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054419","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054419","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"},{"id":"mag:3187928263","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002274122000424","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W2121879602","https://openalex.org/W2143612262","https://openalex.org/W2750499125","https://openalex.org/W2888779557","https://openalex.org/W2938947737","https://openalex.org/W2939111082","https://openalex.org/W2962760690","https://openalex.org/W2963240019","https://openalex.org/W2963362078","https://openalex.org/W2963414781","https://openalex.org/W2963739817","https://openalex.org/W2972991710","https://openalex.org/W3011207290","https://openalex.org/W6638749077","https://openalex.org/W6640059789","https://openalex.org/W6743477263","https://openalex.org/W6746574493","https://openalex.org/W6756286202"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W3040374273","https://openalex.org/W2160451571","https://openalex.org/W2495256954","https://openalex.org/W2259317772"],"abstract_inverted_index":{"The":[0,107],"RNN-Transducer":[1],"(RNNT)":[2],"outperforms":[3],"classic":[4,40,65],"Automatic":[5],"Speech":[6],"Recognition":[7],"(ASR)":[8],"systems":[9],"when":[10,104],"a":[11],"large":[12,35],"amount":[13],"of":[14,33,48],"supervised":[15],"training":[16],"data":[17],"is":[18,53,77],"available.":[19],"For":[20],"low-resource":[21],"languages,":[22],"the":[23,45,49,59,64,70,82,86,91,100,115,120,126,130,135,143,152,156,160,168,171],"RNNT":[24,102,127,136,161],"models":[25],"overfit,":[26],"and":[27,129,163,170],"can":[28],"not":[29,78,112,140],"directly":[30],"take":[31],"advantage":[32],"additional":[34],"text":[36],"corpora":[37],"as":[38,97,99,142],"in":[39,63,145],"ASR":[41,66],"systems.We":[42],"focus":[43],"on":[44,114],"prediction":[46,71,87,92,109,137],"network":[47,72,93,110,138],"RNNT,":[50],"since":[51],"it":[52,124,149],"believed":[54],"to":[55,58,155],"be":[56],"analogous":[57],"Language":[60],"Model":[61],"(LM)":[62],"systems.":[67],"We":[68],"pre-train":[69],"with":[73],"text-only":[74],"data,":[75],"which":[76,89],"helpful.":[79],"Moreover,":[80],"removing":[81],"recurrent":[83],"layers":[84],"from":[85],"network,":[88],"makes":[90],"stateless,":[94],"performs":[95],"virtually":[96],"well":[98],"original":[101],"model,":[103],"using":[105],"wordpieces.":[106],"stateless":[108],"does":[111,139],"depend":[113],"previous":[116],"output":[117],"symbols,":[118],"except":[119],"last":[121],"one.":[122],"Therefore":[123],"simplifies":[125],"architectures":[128],"inference.Our":[131],"results":[132],"suggest":[133],"that":[134],"function":[141],"LM":[144],"classical":[146],"ASR.":[147],"Instead,":[148],"merely":[150],"helps":[151],"model":[153],"align":[154],"input":[157],"audio,":[158],"while":[159],"encoder":[162],"joint":[164],"networks":[165],"capture":[166],"both":[167],"acoustic":[169],"linguistic":[172],"information.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":6}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}