{"id":"https://openalex.org/W7214647992","doi":"https://doi.org/10.48550/arxiv.2609.30839","title":"Attention-Based Adaptive Policies for Simultaneous Speech-to-Text Translation","display_name":"Attention-Based Adaptive Policies for Simultaneous Speech-to-Text Translation","publication_year":2026,"publication_date":"2026-09-25","ids":{"openalex":"https://openalex.org/W7214647992","doi":"https://doi.org/10.48550/arxiv.2609.30839"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.30839","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.30839","pdf_url":"https://arxiv.org/pdf/2609.30839","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.30839","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153301347","display_name":"Filip T\u0103\u015f\u0103dan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"T\u0103\u015f\u0103dan, Filip","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129310858","display_name":"Ema Tomanov\u00e1","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Tomanov\u00e1, Ema","raw_affiliation_strings":["University of Copenhagen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Copenhagen","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129290481","display_name":"Ondrej Lopuch","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Lopuch, Ondrej","raw_affiliation_strings":["University of Copenhagen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Copenhagen","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116290084","display_name":"Pawe\u0142 Bi\u0142ko","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Bilko, Pawe\u0142","raw_affiliation_strings":["University of Copenhagen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Copenhagen","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139768385","display_name":"Anders S\u00f8gaard","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"S\u00f8gaard, Anders","raw_affiliation_strings":["University of Copenhagen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Copenhagen","institution_ids":["https://openalex.org/I124055696"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9945999979972839,"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":0.9945999979972839,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.00279999990016222,"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":0.0017999999690800905,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8281000256538391},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.7319999933242798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5401999950408936},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5200999975204468},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5166000127792358},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.513700008392334},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4887999892234802},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4657999873161316},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.436599999666214},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.3991999924182892},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3707999885082245},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.3440999984741211},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.2971999943256378},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2897000014781952}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.30839","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.30839","pdf_url":"https://arxiv.org/pdf/2609.30839","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.30839","doi":"https://doi.org/10.48550/arxiv.2609.30839","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.30839","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.30839","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.30839","pdf_url":"https://arxiv.org/pdf/2609.30839","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214647992.pdf","grobid_xml":"https://content.openalex.org/works/W7214647992.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4385570121","https://openalex.org/W4402671750","https://openalex.org/W4385822738","https://openalex.org/W7163077856","https://openalex.org/W4416689692","https://openalex.org/W4402671605","https://openalex.org/W4389519071","https://openalex.org/W3034586846","https://openalex.org/W4224325263","https://openalex.org/W3213993043"],"abstract_inverted_index":{"Simultaneous":[0],"speech-to-text":[1,92],"translation":[2,38,93,110,136,151],"(Simul-S2TT)":[3],"consists":[4],"of":[5,23,29,52,128],"generating":[6],"partial":[7],"translations":[8],"while":[9,39,133],"the":[10,17,20,27,31,41,49,53,58,62,67,76,83,113,118,135,143,154],"incoming":[11],"audio":[12],"frames":[13,65],"are":[14],"processed":[15],"by":[16,138],"system.":[18],"However,":[19],"streaming":[21,99],"nature":[22],"this":[24,45,72],"setup":[25],"creates":[26],"challenge":[28],"deciding":[30],"best":[32],"moment":[33],"to":[34,56,95,122,130,147],"perform":[35],"an":[36],"accurate":[37],"minimizing":[40],"delay.":[42],"To":[43],"address":[44],"challenge,":[46],"we":[47,74],"utilize":[48],"cross-attention":[50],"mechanism":[51],"encoder-decoder":[54],"architecture":[55],"find":[57],"right":[59],"alignment":[60],"between":[61],"input":[63],"speech":[64],"and":[66,82],"target":[68],"text":[69],"tokens.":[70],"In":[71],"paper,":[73],"propose":[75],"Recent":[77],"Frame":[78],"Attention":[79,85],"Policy":[80,86],"(RFAP)":[81],"Dual-Condition":[84],"(DCAP)":[87],"that":[88,117],"allow":[89],"offline":[90],"trained":[91],"models":[94],"be":[96],"used":[97],"in":[98],"scenarios":[100],"without":[101],"requiring":[102],"additional":[103],"training.":[104],"Results":[105],"on":[106],"three":[107],"different":[108],"language":[109],"pairs":[111],"over":[112],"CVSS-C":[114],"corpus":[115],"show":[116],"RFAP":[119],"is":[120,145,156],"able":[121,146],"surpass":[123],"other":[124],"policies":[125],"with":[126],"gains":[127],"up":[129],"4.0":[131],"BLEU":[132],"reducing":[134],"delay":[137],"almost":[139],"1":[140],"second.":[141],"Moreover,":[142],"DCAP":[144],"preserve":[148],"a":[149],"high":[150],"quality":[152],"when":[153],"latency":[155],"very":[157],"low.":[158]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-29T00:00:00"}
