{"id":"https://openalex.org/W4210811812","doi":"https://doi.org/10.1109/asru51503.2021.9688101","title":"On Addressing Practical Challenges for RNN-Transducer","display_name":"On Addressing Practical Challenges for RNN-Transducer","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210811812","doi":"https://doi.org/10.1109/asru51503.2021.9688101"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688101","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101987526","display_name":"Rui Zhao","orcid":"https://orcid.org/0000-0002-9699-9984"},"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":"Rui Zhao","raw_affiliation_strings":["Microsoft Speech and Language Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100763213","display_name":"Jian Xue","orcid":"https://orcid.org/0000-0002-9460-802X"},"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":"Jian Xue","raw_affiliation_strings":["Microsoft Speech and Language Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055564488","display_name":"Wenning Wei","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":false,"raw_author_name":"Wenning Wei","raw_affiliation_strings":["Microsoft Speech and Language Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061724331","display_name":"Lei He","orcid":"https://orcid.org/0000-0003-3028-6305"},"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":"Lei He","raw_affiliation_strings":["Microsoft Speech and Language Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"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":"Yifan Gong","raw_affiliation_strings":["Microsoft Speech and Language Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":2.3445,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.91155729,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"526","last_page":"533"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8466600775718689},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6160641312599182},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5964934825897217},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5075725317001343},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4348500967025757},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4214229881763458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4003722369670868}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8466600775718689},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6160641312599182},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5964934825897217},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5075725317001343},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4348500967025757},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4214229881763458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4003722369670868},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688101","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2028825255","https://openalex.org/W2132051730","https://openalex.org/W2294543795","https://openalex.org/W2327501763","https://openalex.org/W2594610113","https://openalex.org/W2766219058","https://openalex.org/W2889385306","https://openalex.org/W2903853691","https://openalex.org/W2912668608","https://openalex.org/W2955856352","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2963211739","https://openalex.org/W2963827914","https://openalex.org/W2963970535","https://openalex.org/W2972880214","https://openalex.org/W3007227084","https://openalex.org/W3008008574","https://openalex.org/W3015194534","https://openalex.org/W3015639015","https://openalex.org/W3016010032","https://openalex.org/W3016155933","https://openalex.org/W3093972948","https://openalex.org/W3094667432","https://openalex.org/W3095311338","https://openalex.org/W3096524176","https://openalex.org/W3112702554","https://openalex.org/W3119563486","https://openalex.org/W3150122400","https://openalex.org/W3161324588","https://openalex.org/W3161873870","https://openalex.org/W3163907627","https://openalex.org/W4288088457","https://openalex.org/W4385245566","https://openalex.org/W6638749077","https://openalex.org/W6657520753","https://openalex.org/W6679659736","https://openalex.org/W6741807409","https://openalex.org/W6769806307","https://openalex.org/W6774912157","https://openalex.org/W6784418856","https://openalex.org/W6787432340","https://openalex.org/W6903921188","https://openalex.org/W7027429494"],"related_works":["https://openalex.org/W2114089658","https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1769849273","https://openalex.org/W1574295218","https://openalex.org/W113247760","https://openalex.org/W1967477266","https://openalex.org/W2547793174","https://openalex.org/W2070212102","https://openalex.org/W2132658536"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"several":[3],"works":[4],"are":[5,22],"proposed":[6,144],"to":[7,28,77,130],"address":[8],"practi-cal":[9],"challenges":[10,21],"for":[11,85],"deploying":[12],"RNN":[13],"Transducer":[14],"(RNN-T)":[15],"based":[16],"speech":[17,59,131],"recognition":[18,167],"systems.":[19],"These":[20],"adapting":[23],"a":[24,29,52,71,109],"well-trained":[25],"RNN-T":[26,79],"model":[27,80],"new":[30],"domain":[31,65],"without":[32],"col-lecting":[33],"the":[34,48,58,63,78,83,86,117,123,128,158,166],"audio":[35],"data,":[36,116],"obtaining":[37],"time":[38,69,145],"stamps":[39],"and":[40,107,125,135],"confidence":[41,96,173],"scores":[42,97],"at":[43],"word":[44,94,138,154],"level.":[45],"We":[46,169],"solve":[47],"first":[49],"challenge":[50],"with":[51,113,127,176],"splicing":[53,118],"data":[54,119],"method":[55,121,132,147],"which":[56],"concatenates":[57],"segments":[60],"ex-tracted":[61],"from":[62,108,157],"source":[64],"data.":[66],"To":[67],"get":[68,149],"stamps,":[70],"phone":[72],"prediction":[73],"branch":[74],"is":[75],"added":[76],"by":[81,98,133],"sharing":[82],"encoder":[84],"purpose":[87],"of":[88,102],"forced":[89],"alignment.":[90],"Fi-nally,":[91],"we":[92],"obtain":[93,171],"level":[95],"utilizing":[99],"sev-eral":[100],"types":[101],"features":[103],"calculated":[104],"during":[105],"decoding":[106],"confusion":[110],"network.":[111],"Evaluated":[112],"Microsoft":[114],"production":[115],"adaptation":[120,126],"improves":[122],"base-line":[124],"text":[129],"58.03%":[134],"15.25%":[136],"relative":[137],"error":[139],"rate":[140],"reduction,":[141],"respectively.":[142],"The":[143],"stamping":[146],"can":[148],"less":[150],"than":[151],"50":[152],"mil-lisecond":[153],"timing":[155],"difference":[156],"ground":[159],"truth":[160],"align-ment":[161],"on":[162],"average":[163],"while":[164],"maintaining":[165],"accuracy.":[168],"also":[170],"high":[172],"annotation":[174],"performance":[175],"limited":[177],"computation":[178],"cost.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":9}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}