{"id":"https://openalex.org/W3144557079","doi":"https://doi.org/10.1109/slt48900.2021.9383548","title":"Improving RNN Transducer Based ASR with Auxiliary Tasks","display_name":"Improving RNN Transducer Based ASR with Auxiliary Tasks","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3144557079","doi":"https://doi.org/10.1109/slt48900.2021.9383548","mag":"3144557079"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5069296252","display_name":"Chunxi Liu","orcid":"https://orcid.org/0000-0001-5441-9374"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chunxi Liu","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085650357","display_name":"Feida Zhang","orcid":"https://orcid.org/0000-0002-1220-8824"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank Zhang","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103098852","display_name":"Duc Le","orcid":"https://orcid.org/0000-0001-9490-2563"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Duc Le","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062940343","display_name":"Suyoun Kim","orcid":"https://orcid.org/0000-0002-6822-337X"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suyoun Kim","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051165898","display_name":"Yatharth Saraf","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yatharth Saraf","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069954850","display_name":"Geoffrey Zweig","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Geoffrey Zweig","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5069296252"],"corresponding_institution_ids":["https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":4.351,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.95179345,"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":"172","last_page":"179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9975000023841858,"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":0.9958999752998352,"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":0.8378801345825195},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8375172019004822},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.666347324848175},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6542521119117737},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6470090746879578},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.527388334274292},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5187892317771912},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45529890060424805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45177242159843445},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4400272071361542},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4229845404624939}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8378801345825195},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8375172019004822},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.666347324848175},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6542521119117737},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6470090746879578},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.527388334274292},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5187892317771912},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45529890060424805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45177242159843445},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4400272071361542},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4229845404624939},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/slt48900.2021.9383548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W1026270304","https://openalex.org/W1494198834","https://openalex.org/W1506752962","https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W1899504021","https://openalex.org/W2097117768","https://openalex.org/W2147768505","https://openalex.org/W2158069733","https://openalex.org/W2168894214","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2521999726","https://openalex.org/W2551887912","https://openalex.org/W2620998106","https://openalex.org/W2746192915","https://openalex.org/W2889030467","https://openalex.org/W2902347140","https://openalex.org/W2906424389","https://openalex.org/W2913340405","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2950621961","https://openalex.org/W2950872548","https://openalex.org/W2962760690","https://openalex.org/W2963240019","https://openalex.org/W2963250244","https://openalex.org/W2963303028","https://openalex.org/W2963414781","https://openalex.org/W2963606038","https://openalex.org/W2963827914","https://openalex.org/W2964084166","https://openalex.org/W2964121744","https://openalex.org/W2972899427","https://openalex.org/W2981857663","https://openalex.org/W2983490653","https://openalex.org/W2990501692","https://openalex.org/W3007227084","https://openalex.org/W3008181812","https://openalex.org/W3008525923","https://openalex.org/W3008898571","https://openalex.org/W3014408449","https://openalex.org/W3015194534","https://openalex.org/W3015315932","https://openalex.org/W3015654466","https://openalex.org/W3015960524","https://openalex.org/W3015995734","https://openalex.org/W3016010032","https://openalex.org/W3025165719","https://openalex.org/W3029982911","https://openalex.org/W3035216398","https://openalex.org/W3095311338","https://openalex.org/W3095697114","https://openalex.org/W3097558625","https://openalex.org/W3097777922","https://openalex.org/W3142252347","https://openalex.org/W3146505093","https://openalex.org/W3150637114","https://openalex.org/W6626481562","https://openalex.org/W6631190155","https://openalex.org/W6631636882","https://openalex.org/W6638749077","https://openalex.org/W6684665197","https://openalex.org/W6713762819","https://openalex.org/W6729556111","https://openalex.org/W6741807409","https://openalex.org/W6756732229","https://openalex.org/W6757068045","https://openalex.org/W6770425081","https://openalex.org/W6775557069","https://openalex.org/W6785660780","https://openalex.org/W6786215725"],"related_works":["https://openalex.org/W3008584592","https://openalex.org/W2160451571","https://openalex.org/W3049463507","https://openalex.org/W2936497627","https://openalex.org/W4288365749","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W4287598411","https://openalex.org/W3098382480","https://openalex.org/W2495256954"],"abstract_inverted_index":{"End-to-end":[0],"automatic":[1],"speech":[2,20],"recognition":[3],"(ASR)":[4],"models":[5],"with":[6,84],"a":[7],"single":[8],"neural":[9,24],"network":[10,25],"have":[11],"recently":[12],"demonstrated":[13],"state-of-the-art":[14],"results":[15,132],"compared":[16,140],"to":[17,141],"conventional":[18,76],"hybrid":[19,77],"recognizers.":[21],"Specifically,":[22],"recurrent":[23],"transducer":[26],"(RNN-T)":[27],"has":[28],"shown":[29],"competitive":[30,131],"ASR":[31,48,65,94],"performance":[32,95],"on":[33,96,135],"various":[34],"benchmarks.":[35],"In":[36,79],"this":[37],"work,":[38],"we":[39,89,113],"examine":[40],"ways":[41],"in":[42,75,121],"which":[43],"RNN-T":[44,64,127],"can":[45],"achieve":[46],"better":[47],"accuracy":[49],"via":[50],"performing":[51,69,144],"auxiliary":[52,60,117],"tasks.":[53],"We":[54,103],"propose":[55],"(i)":[56],"using":[57],"the":[58,92],"same":[59],"task":[61],"as":[62,74,139],"primary":[63],"task,":[66],"and":[67,101],"(ii)":[68],"context-dependent":[70],"graphemic":[71],"state":[72],"prediction":[73],"modeling.":[78],"transcribing":[80],"social":[81],"media":[82],"videos":[83],"varying":[85],"training":[86],"data":[87],"size,":[88],"first":[90],"evaluate":[91],"streaming":[93],"three":[97],"languages:":[98],"Romanian,":[99],"Turkish":[100],"German.":[102],"find":[104],"that":[105,115],"both":[106,116],"proposed":[107],"methods":[108],"provide":[109],"consistent":[110],"improvements.":[111],"Next,":[112],"observe":[114],"tasks":[118],"demonstrate":[119],"efficacy":[120],"learning":[122],"deep":[123],"transformer":[124],"encoders":[125],"for":[126],"criterion,":[128],"thus":[129],"achieving":[130],"-2.0%/4.2%":[133],"WER":[134],"LibriSpeech":[136],"test-clean/other":[137],"-":[138],"prior":[142],"top":[143],"models.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}