{"id":"https://openalex.org/W4391021779","doi":"https://doi.org/10.1109/asru57964.2023.10389715","title":"Token-Level Serialized Output Training for Joint Streaming ASR and ST Leveraging Textual Alignments","display_name":"Token-Level Serialized Output Training for Joint Streaming ASR and ST Leveraging Textual Alignments","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021779","doi":"https://doi.org/10.1109/asru57964.2023.10389715"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5070385491","display_name":"Sara Papi","orcid":"https://orcid.org/0000-0002-4494-8886"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]},{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sara Papi","raw_affiliation_strings":["Fondazione Bruno Kessler and University of Trento,Italy","Fondazione Bruno Kessler and University of Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler and University of Trento,Italy","institution_ids":["https://openalex.org/I193223587","https://openalex.org/I2277624104"]},{"raw_affiliation_string":"Fondazione Bruno Kessler and University of Trento, Italy","institution_ids":["https://openalex.org/I193223587","https://openalex.org/I2277624104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062250845","display_name":"Peidong Wang","orcid":"https://orcid.org/0000-0002-7042-0209"},"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":"Peidong Wang","raw_affiliation_strings":["Microsoft,USA","Microsoft, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034556928","display_name":"Junkun Chen","orcid":"https://orcid.org/0000-0003-0193-238X"},"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":"Junkun Chen","raw_affiliation_strings":["Microsoft,USA","Microsoft, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, USA","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,USA","Microsoft, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, USA","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,USA","Microsoft, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034136587","display_name":"Yashesh Gaur","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":"Yashesh Gaur","raw_affiliation_strings":["Microsoft,USA","Microsoft, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/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/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.9015123844146729},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8723921775817871},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7140855193138123},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6024668216705322},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5739377737045288},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.43459463119506836},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10082894563674927},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08229181170463562},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06213083863258362}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.9015123844146729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8723921775817871},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7140855193138123},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6024668216705322},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5739377737045288},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.43459463119506836},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10082894563674927},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08229181170463562},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06213083863258362},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"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":51,"referenced_works":["https://openalex.org/W2020270617","https://openalex.org/W2089629691","https://openalex.org/W2144499799","https://openalex.org/W2168995909","https://openalex.org/W2887005286","https://openalex.org/W2951456627","https://openalex.org/W2962757645","https://openalex.org/W2963250244","https://openalex.org/W2963532001","https://openalex.org/W2976556660","https://openalex.org/W3015671919","https://openalex.org/W3015974384","https://openalex.org/W3016010032","https://openalex.org/W3037793211","https://openalex.org/W3094821064","https://openalex.org/W3096686110","https://openalex.org/W3102811925","https://openalex.org/W3105681039","https://openalex.org/W3113676066","https://openalex.org/W3152534858","https://openalex.org/W3155609600","https://openalex.org/W3160201895","https://openalex.org/W3161873870","https://openalex.org/W3162665866","https://openalex.org/W3163907627","https://openalex.org/W3174032041","https://openalex.org/W3183186840","https://openalex.org/W3195179105","https://openalex.org/W3196509775","https://openalex.org/W3211278025","https://openalex.org/W3213993043","https://openalex.org/W3214897310","https://openalex.org/W4221145476","https://openalex.org/W4224137820","https://openalex.org/W4226491018","https://openalex.org/W4281653986","https://openalex.org/W4285273653","https://openalex.org/W4287855189","https://openalex.org/W4288088457","https://openalex.org/W4372267638","https://openalex.org/W4375868938","https://openalex.org/W4375869197","https://openalex.org/W4385571513","https://openalex.org/W4385823495","https://openalex.org/W4391021781","https://openalex.org/W6739901393","https://openalex.org/W6757817989","https://openalex.org/W6769806307","https://openalex.org/W6784851026","https://openalex.org/W6810202124","https://openalex.org/W6846175339"],"related_works":["https://openalex.org/W2970530566","https://openalex.org/W2967478618","https://openalex.org/W2997152889","https://openalex.org/W4385572700","https://openalex.org/W4388335561","https://openalex.org/W4307309205","https://openalex.org/W4288261899","https://openalex.org/W4385009901","https://openalex.org/W4389115113","https://openalex.org/W3016124757"],"abstract_inverted_index":{"In":[0],"real-world":[1],"applications,":[2],"users":[3],"often":[4],"require":[5],"both":[6],"translations":[7],"and":[8,38,50,69,82,102,122,132],"transcriptions":[9],"of":[10,100,105,129],"speech":[11,35,39],"to":[12,119],"enhance":[13],"their":[14],"comprehension,":[15],"particularly":[16],"in":[17,79,135],"streaming":[18,29],"scenarios":[19],"where":[20],"incremental":[21],"generation":[22],"is":[23],"necessary.":[24],"This":[25],"paper":[26],"introduces":[27],"a":[28,44,59],"Transformer-Transducer":[30],"that":[31,66,87],"jointly":[32],"generates":[33],"automatic":[34],"recognition":[36],"(ASR)":[37],"translation":[40],"(ST)":[41],"outputs":[42],"using":[43],"single":[45],"decoder.":[46],"To":[47],"produce":[48],"ASR":[49,98,121],"ST":[51,103,123],"content":[52],"effectively":[53],"with":[54],"minimal":[55],"latency,":[56],"we":[57],"propose":[58],"joint":[60],"token-level":[61],"serialized":[62],"output":[63,116],"training":[64],"method":[65],"interleaves":[67],"source":[68],"target":[70],"words":[71],"by":[72],"leveraging":[73],"an":[74,96,126],"off-the-shelf":[75],"textual":[76],"aligner.":[77],"Experiments":[78],"monolingual":[80],"(it-en)":[81],"multilingual":[83,137],"({de,es,it}-en)":[84],"settings":[85],"demonstrate":[86],"our":[88,108],"approach":[89],"achieves":[90],"the":[91,136],"best":[92],"quality-latency":[93],"balance.":[94],"With":[95],"average":[97,127],"latency":[99,104],"1s":[101],"$1.3":[106],"\\mathrm{~s}$,":[107],"model":[109],"shows":[110],"no":[111],"degradation":[112],"or":[113],"even":[114],"improves":[115],"quality":[117],"compared":[118],"separate":[120],"models,":[124],"yielding":[125],"improvement":[128],"1.1":[130],"WER":[131],"0.4":[133],"BLEU":[134],"case.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}