{"id":"https://openalex.org/W3161873870","doi":"https://doi.org/10.1109/icassp39728.2021.9413535","title":"Developing Real-Time Streaming Transformer Transducer for Speech Recognition on Large-Scale Dataset","display_name":"Developing Real-Time Streaming Transformer Transducer for Speech Recognition on Large-Scale Dataset","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161873870","doi":"https://doi.org/10.1109/icassp39728.2021.9413535","mag":"3161873870"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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":null,"display_name":"Xie Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xie Chen","raw_affiliation_strings":["Microsoft Speech and Language Group"],"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101709477","display_name":"Yu Wu","orcid":"https://orcid.org/0000-0002-5715-3011"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wu","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101767354","display_name":"Zhenghao Wang","orcid":"https://orcid.org/0000-0003-2676-7683"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenghao Wang","raw_affiliation_strings":["Microsoft Speech and Language Group"],"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-2599-6752"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Speech and Language Group"],"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":19.7381,"has_fulltext":false,"cited_by_count":170,"citation_normalized_percentile":{"value":0.99497252,"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":"5904","last_page":"5908"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9991999864578247,"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":0.7621821165084839},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7118850946426392},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6012069582939148},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.601048469543457},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.5369076728820801},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5242986083030701},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5219947099685669},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4906424582004547},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.350372314453125},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.35003942251205444},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1506434977054596},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1416603922843933},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10018232464790344},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10002830624580383},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09294939041137695}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7621821165084839},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7118850946426392},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6012069582939148},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.601048469543457},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.5369076728820801},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5242986083030701},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5219947099685669},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4906424582004547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.350372314453125},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.35003942251205444},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1506434977054596},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1416603922843933},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10018232464790344},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10002830624580383},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09294939041137695},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1828163288","https://openalex.org/W2064675550","https://openalex.org/W2133564696","https://openalex.org/W2327501763","https://openalex.org/W2750499125","https://openalex.org/W2892009249","https://openalex.org/W2936123380","https://openalex.org/W2939248538","https://openalex.org/W2953022181","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2963403868","https://openalex.org/W2963414781","https://openalex.org/W2963827914","https://openalex.org/W2963925437","https://openalex.org/W2963970535","https://openalex.org/W2964084166","https://openalex.org/W2964110616","https://openalex.org/W2964272710","https://openalex.org/W2964308564","https://openalex.org/W2972818416","https://openalex.org/W2981857663","https://openalex.org/W2987019345","https://openalex.org/W3007328579","https://openalex.org/W3012775809","https://openalex.org/W3015671919","https://openalex.org/W3015974384","https://openalex.org/W3016010032","https://openalex.org/W3025165719","https://openalex.org/W3026287411","https://openalex.org/W3092122846","https://openalex.org/W3093346109","https://openalex.org/W3094667432","https://openalex.org/W3095311338","https://openalex.org/W3096702180","https://openalex.org/W3096888553","https://openalex.org/W3097125541","https://openalex.org/W3097777922","https://openalex.org/W3162665866","https://openalex.org/W4288088457","https://openalex.org/W4294619417","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6679434410","https://openalex.org/W6739901393","https://openalex.org/W6741807409","https://openalex.org/W6747158283","https://openalex.org/W6747753452","https://openalex.org/W6754299077","https://openalex.org/W6769806307","https://openalex.org/W6770245836","https://openalex.org/W6784400248","https://openalex.org/W6784800133","https://openalex.org/W6784916438"],"related_works":["https://openalex.org/W2072454424","https://openalex.org/W4384820447","https://openalex.org/W2185942010","https://openalex.org/W2260725127","https://openalex.org/W2117438306","https://openalex.org/W2004297762","https://openalex.org/W1992056405","https://openalex.org/W767846903","https://openalex.org/W4200299863","https://openalex.org/W2221419418"],"abstract_inverted_index":{"Recently,":[0],"Transformer":[1,26,45,79,95],"based":[2],"end-to-end":[3],"models":[4,48],"have":[5],"achieved":[6],"great":[7],"success":[8],"in":[9,99],"many":[10],"areas":[11],"including":[12],"speech":[13],"recognition.":[14],"However,":[15],"compared":[16],"to":[17,33,75],"LSTM":[18],"models,":[19],"the":[20,25,42,50,66,87,100,104],"heavy":[21],"computational":[22],"cost":[23,106],"of":[24,44,68],"during":[27],"inference":[28],"is":[29],"a":[30,61,77,113],"key":[31],"issue":[32],"prevent":[34],"their":[35],"applications.":[36],"In":[37],"this":[38],"work,":[39],"we":[40],"explored":[41],"potential":[43],"Transducer":[46,80,91],"(T-T)":[47],"for":[49],"fist":[51],"pass":[52],"decoding":[53],"with":[54,112],"low":[55],"latency":[56,108],"and":[57,71,93,107],"fast":[58],"speed":[59],"on":[60],"large-scale":[62],"dataset.":[63],"We":[64,82],"combine":[65],"idea":[67],"Transformer-":[69],"XL":[70],"chunk-wise":[72],"streaming":[73,101],"processing":[74],"design":[76],"streamable":[78,94],"model.":[81],"demonstrate":[83],"that":[84],"T-T":[85],"outperforms":[86],"hybrid":[88],"model,":[89],"RNN":[90],"(RNN-T),":[92],"attention-based":[96],"encoder-decoder":[97],"model":[98],"scenario.":[102],"Furthermore,":[103],"runtime":[105],"can":[109],"be":[110],"optimized":[111],"relatively":[114],"small":[115],"look-ahead.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":56},{"year":2022,"cited_by_count":40},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}