{"id":"https://openalex.org/W4392910316","doi":"https://doi.org/10.1109/icassp48485.2024.10447565","title":"Leveraging Timestamp Information for Serialized Joint Streaming Recognition and Translation","display_name":"Leveraging Timestamp Information for Serialized Joint Streaming Recognition and Translation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910316","doi":"https://doi.org/10.1109/icassp48485.2024.10447565"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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":"Sara Papi","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/A5062250845","display_name":"Peidong Wang","orcid":"https://orcid.org/0000-0002-7042-0209"},"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":"Peidong Wang","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/A5034556928","display_name":"Junkun Chen","orcid":"https://orcid.org/0000-0003-0193-238X"},"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":"Junkun Chen","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/A5100763213","display_name":"Jian Xue","orcid":"https://orcid.org/0000-0002-9460-802X"},"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":"Jian Xue","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/A5016279564","display_name":"Naoyuki Kanda","orcid":"https://orcid.org/0000-0002-8628-3288"},"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":"Naoyuki Kanda","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/A5100365071","display_name":"Jinyu Li","orcid":"https://orcid.org/0009-0006-9478-0096"},"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":"Jinyu Li","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":"last","author":{"id":"https://openalex.org/A5034136587","display_name":"Yashesh Gaur","orcid":null},"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":"Yashesh Gaur","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"]}]}],"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":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10381","last_page":"10385"},"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":0.9995999932289124,"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":0.9966999888420105,"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/timestamp","display_name":"Timestamp","score":0.8841578364372253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8738440275192261},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.8380483388900757},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5790531635284424},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5365669131278992},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5309925079345703},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5059978365898132},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5037025809288025},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.48076483607292175},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4329088628292084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34024155139923096},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3220069408416748},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.13875430822372437},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08831942081451416}],"concepts":[{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.8841578364372253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8738440275192261},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8380483388900757},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5790531635284424},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5365669131278992},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5309925079345703},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5059978365898132},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5037025809288025},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.48076483607292175},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4329088628292084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34024155139923096},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3220069408416748},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13875430822372437},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08831942081451416},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":29,"referenced_works":["https://openalex.org/W2144499799","https://openalex.org/W2404511972","https://openalex.org/W2550821151","https://openalex.org/W2747874407","https://openalex.org/W2887005286","https://openalex.org/W2963250244","https://openalex.org/W2963532001","https://openalex.org/W3016010032","https://openalex.org/W3094612203","https://openalex.org/W3102811925","https://openalex.org/W3105681039","https://openalex.org/W3152534858","https://openalex.org/W3161873870","https://openalex.org/W3183186840","https://openalex.org/W3196509775","https://openalex.org/W3211278025","https://openalex.org/W3214897310","https://openalex.org/W4226491018","https://openalex.org/W4281653986","https://openalex.org/W4281775950","https://openalex.org/W4287855189","https://openalex.org/W4288088457","https://openalex.org/W4289593661","https://openalex.org/W4319862635","https://openalex.org/W4385245566","https://openalex.org/W4391021779","https://openalex.org/W6752242417","https://openalex.org/W6757817989","https://openalex.org/W6785030709"],"related_works":["https://openalex.org/W2060561905","https://openalex.org/W1417711376","https://openalex.org/W1986883493","https://openalex.org/W2469862403","https://openalex.org/W2166378262","https://openalex.org/W2035891203","https://openalex.org/W4379524643","https://openalex.org/W2367807705","https://openalex.org/W2070290693","https://openalex.org/W4304700937"],"abstract_inverted_index":{"The":[0],"growing":[1],"need":[2],"for":[3,28,90,131],"instant":[4],"spoken":[5],"language":[6],"transcription":[7,78],"and":[8,16,38,54,76,79,104],"translation":[9,40,80],"is":[10],"driven":[11],"by":[12],"increased":[13,55],"global":[14],"communication":[15],"cross-lingual":[17],"interactions.":[18],"This":[19],"has":[20],"made":[21],"offering":[22],"translations":[23],"in":[24,51,58,107],"multiple":[25],"languages":[26],"essential":[27],"user":[29],"applications.":[30],"Traditional":[31],"approaches":[32],"to":[33,49,72,100],"automatic":[34],"speech":[35,39],"recognition":[36],"(ASR)":[37],"(ST)":[41],"have":[42],"often":[43],"relied":[44],"on":[45,97,112],"separate":[46],"systems,":[47],"leading":[48],"inefficiencies":[50],"computational":[52],"resources,":[53],"synchronization":[56],"complexity":[57],"real":[59],"time.":[60,134],"In":[61],"this":[62],"paper,":[63],"we":[64],"propose":[65],"a":[66,82,87,128],"streaming":[67,109],"Transformer-Transducer":[68],"(T-T)":[69],"model":[70],"able":[71],"jointly":[73],"produce":[74,102],"many-to-one":[75],"one-to-many":[77,124],"using":[81],"single":[83,129],"decoder.":[84],"We":[85],"introduce":[86],"novel":[88],"method":[89],"joint":[91,125],"token-level":[92],"serialized":[93],"output":[94],"training":[95],"based":[96],"timestamp":[98],"information":[99],"effectively":[101],"ASR":[103],"ST":[105],"outputs":[106,126],"the":[108,115,121,132],"setting.":[110],"Experiments":[111],"{it,es,de}\u2194en":[113],"prove":[114],"effectiveness":[116],"of":[117,123],"our":[118],"approach,":[119],"enabling":[120],"generation":[122],"with":[127],"decoder":[130],"first":[133]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}