{"id":"https://openalex.org/W4412888729","doi":"https://doi.org/10.18653/v1/2025.findings-acl.157","title":"InfiniSST: Simultaneous Translation of Unbounded Speech with Large Language Model","display_name":"InfiniSST: Simultaneous Translation of Unbounded Speech with Large Language Model","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888729","doi":"https://doi.org/10.18653/v1/2025.findings-acl.157"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.157","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.157","pdf_url":"https://aclanthology.org/2025.findings-acl.157.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.157.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057636712","display_name":"Siqi Ouyang","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siqi Ouyang","raw_affiliation_strings":["Carnegie Mellon University , Language Technologies Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University , Language Technologies Institute","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101225200","display_name":"Xi Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xi Xu","raw_affiliation_strings":["Carnegie Mellon University , Language Technologies Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University , Language Technologies Institute","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440407","display_name":"Lei Li","orcid":"https://orcid.org/0000-0003-3095-9776"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Li","raw_affiliation_strings":["Carnegie Mellon University , Language Technologies Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University , Language Technologies Institute","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3032","last_page":"3046"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9866999983787537,"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":0.9866999983787537,"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":0.9810000061988831,"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":0.9506000280380249,"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":0.7546221017837524},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.667852520942688},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6573536992073059},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42783230543136597},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42519310116767883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3830089569091797},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.3301353454589844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7546221017837524},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.667852520942688},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6573536992073059},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42783230543136597},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42519310116767883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3830089569091797},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3301353454589844},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.157","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.157","pdf_url":"https://aclanthology.org/2025.findings-acl.157.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.157","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.157","pdf_url":"https://aclanthology.org/2025.findings-acl.157.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888729.pdf","grobid_xml":"https://content.openalex.org/works/W4412888729.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4387725353"],"related_works":["https://openalex.org/W2775554247","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2110168585","https://openalex.org/W3107474891","https://openalex.org/W2250213760","https://openalex.org/W4386247111","https://openalex.org/W4327642362","https://openalex.org/W2587014613","https://openalex.org/W123774389"],"abstract_inverted_index":{"Simultaneous":[0],"translation":[1,62,67,112],"of":[2,63,122],"unbounded":[3,64],"streaming":[4],"speech":[5,19],"remains":[6],"a":[7,49,56,81],"challenging":[8],"problem":[9],"due":[10],"to":[11,87,105,115],"the":[12,17,110,120],"need":[13],"for":[14],"effectively":[15],"processing":[16],"historical":[18],"context":[20],"and":[21,27,69,79,95,126],"past":[22],"translations":[23],"so":[24],"that":[25,52,98],"quality":[26,113],"latency,":[28],"including":[29],"computation":[30],"overhead,":[31],"can":[32],"be":[33],"balanced.Most":[34],"prior":[35],"works":[36],"assume":[37],"pre-segmented":[38],"speech,":[39],"limiting":[40],"their":[41],"real-world":[42],"applicability.In":[43],"this":[44],"paper,":[45],"we":[46],"propose":[47],"InfiniSST,":[48],"novel":[50],"approach":[51],"formulates":[53],"SST":[54],"as":[55],"multi-turn":[57],"dialogue":[58],"task,":[59],"enabling":[60],"seamless":[61],"speech.We":[65],"construct":[66],"trajectories":[68],"robust":[70],"segments":[71],"from":[72],"MuST-C":[73,92],"with":[74],"multilatency":[75],"augmentation":[76],"during":[77],"training":[78],"develop":[80],"key-value":[82],"(KV)":[83],"cache":[84,127],"management":[85,128],"strategy":[86,129],"facilitate":[88],"efficient":[89],"inference.Experiments":[90],"on":[91],"En-Es,":[93],"En-De,":[94],"En-Zh":[96],"demonstrate":[97],"InfiniSST":[99],"reduces":[100],"computation-aware":[101],"latency":[102],"by":[103],"0.5":[104],"1":[106,130],"second":[107],"while":[108],"maintaining":[109],"same":[111],"compared":[114],"baselines.Ablation":[116],"studies":[117],"further":[118],"validate":[119],"contributions":[121],"our":[123],"data":[124],"construction":[125],".":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}