{"id":"https://openalex.org/W4408354344","doi":"https://doi.org/10.1109/icassp49660.2025.10890381","title":"Transcribing and Translating, Fast and Slow: Joint Speech Translation and Recognition","display_name":"Transcribing and Translating, Fast and Slow: Joint Speech Translation and Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354344","doi":"https://doi.org/10.1109/icassp49660.2025.10890381"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5071286568","display_name":"Niko Moritz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niko Moritz","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004148531","display_name":"Ruiming Xie","orcid":"https://orcid.org/0009-0003-8315-7491"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruiming Xie","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034136587","display_name":"Yashesh Gaur","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yashesh Gaur","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343462","display_name":"Ke Li","orcid":"https://orcid.org/0000-0001-9206-0892"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Li","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118940826","display_name":"Simone Merello Zeeshan Ahmed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simone Merello Zeeshan Ahmed","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072932051","display_name":"Frank Seide","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank Seide","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047073253","display_name":"Christian Fuegen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christian Fuegen","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7412999868392944,"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":0.7412999868392944,"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/computer-science","display_name":"Computer science","score":0.7722774744033813},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7398757934570312},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7147157192230225},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6553680896759033},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.6246256828308105},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5703612565994263},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4752987325191498},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.3790760040283203},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09225305914878845}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7722774744033813},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7398757934570312},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7147157192230225},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6553680896759033},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.6246256828308105},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5703612565994263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4752987325191498},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3790760040283203},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09225305914878845},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/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/icassp49660.2025.10890381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2144499799","https://openalex.org/W2161192091","https://openalex.org/W2962760690","https://openalex.org/W2972448360","https://openalex.org/W3007142233","https://openalex.org/W3155609600","https://openalex.org/W3173767661","https://openalex.org/W3175301726","https://openalex.org/W3197654132","https://openalex.org/W3207629995","https://openalex.org/W3213993043","https://openalex.org/W4224137820","https://openalex.org/W4226491018","https://openalex.org/W4284883478","https://openalex.org/W4297841343","https://openalex.org/W4319862635","https://openalex.org/W4385822839","https://openalex.org/W4385823495","https://openalex.org/W4391021779","https://openalex.org/W4392909605","https://openalex.org/W4402112050","https://openalex.org/W4402671605","https://openalex.org/W4402671750","https://openalex.org/W4403640425","https://openalex.org/W6717262007","https://openalex.org/W6784447870","https://openalex.org/W6852500804","https://openalex.org/W6859516221"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W4301342010","https://openalex.org/W158465921","https://openalex.org/W3151736118","https://openalex.org/W2279116787","https://openalex.org/W4362495644","https://openalex.org/W2261315194","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W123774389"],"abstract_inverted_index":{"We":[0,57,120],"propose":[1],"the":[2,12,69,82,109],"joint":[3],"speech":[4,21,25,64,76],"translation":[5,26,105],"and":[6,24,32,42,54,84,112,137],"recognition":[7,22],"(JSTAR)":[8],"model":[9,29,70,89,107,132],"that":[10,38],"leverages":[11],"fast-slow":[13],"cascaded":[14,130],"encoder":[15],"architecture":[16],"for":[17,108,115],"simultaneous":[18],"end-to-end":[19],"automatic":[20],"(ASR)":[23],"(ST).":[27],"The":[28],"is":[30,71],"transducer-based":[31,102],"uses":[33],"a":[34,61,85,101,128],"multi-objective":[35],"training":[36,99],"strategy":[37],"optimizes":[39],"both":[40,134],"ASR":[41,53],"ST":[43,55,131],"objectives":[44],"simultaneously.":[45],"This":[46],"allows":[47],"JSTAR":[48,59,125],"to":[49,74,81,94,127],"produce":[50],"high-quality":[51],"streaming":[52,103],"results.":[56],"apply":[58],"in":[60,133],"bilingual":[62],"conversational":[63,86],"setting":[65],"with":[66],"smart-glasses,":[67],"where":[68],"also":[72],"trained":[73],"distinguish":[75],"from":[77],"different":[78],"directions":[79],"corresponding":[80],"wearer":[83],"partner.":[87],"Different":[88],"pre-training":[90],"strategies":[91],"are":[92],"studied":[93],"further":[95],"improve":[96],"results,":[97],"including":[98],"of":[100,118,124],"machine":[104],"(MT)":[106],"first":[110],"time":[111],"applying":[113],"it":[114],"parameter":[116],"initialization":[117],"JSTAR.":[119],"demonstrate":[121],"superior":[122],"performances":[123],"compared":[126],"strong":[129],"BLEU":[135],"scores":[136],"latency.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
