{"id":"https://openalex.org/W4412945113","doi":"https://doi.org/10.18653/v1/2025.acl-long.817","title":"SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation","display_name":"SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945113","doi":"https://doi.org/10.18653/v1/2025.acl-long.817"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.817","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.817","pdf_url":"https://aclanthology.org/2025.acl-long.817.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.817.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068367173","display_name":"Keqi Deng","orcid":"https://orcid.org/0000-0003-1490-963X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keqi Deng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090739497","display_name":"Wenxi Chen","orcid":"https://orcid.org/0000-0002-7938-9033"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenxi Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329117","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-5801-2571"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Phil Woodland","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16718","last_page":"16734"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9175000190734863,"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":0.9085999727249146,"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/speech-translation","display_name":"Speech translation","score":0.7216493487358093},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.693609356880188},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6717098951339722},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.639415979385376},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.556263267993927},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40179920196533203},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38136017322540283},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.27010178565979004},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.0678427517414093}],"concepts":[{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7216493487358093},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.693609356880188},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6717098951339722},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.639415979385376},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.556263267993927},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40179920196533203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38136017322540283},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.27010178565979004},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0678427517414093},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.817","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.817","pdf_url":"https://aclanthology.org/2025.acl-long.817.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.817","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.817","pdf_url":"https://aclanthology.org/2025.acl-long.817.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G581313191","display_name":null,"funder_award_id":"EP/T022159/","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7002347110","display_name":"Cambridge Service for Data Driven Discovery (CSD3) - A National Data Intensive Science Cloud for Converged Simulation, AI & Analytics","funder_award_id":"EP/T022159/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320321848","display_name":"Cambridge Trust","ror":"https://ror.org/05sprqy15"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945113.pdf","grobid_xml":"https://content.openalex.org/works/W4412945113.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4301342010","https://openalex.org/W158465921","https://openalex.org/W2279116787","https://openalex.org/W2261315194","https://openalex.org/W2055243143","https://openalex.org/W2099033952","https://openalex.org/W2520872336","https://openalex.org/W2339399820","https://openalex.org/W2338806053","https://openalex.org/W123774389"],"abstract_inverted_index":{"Simultaneous":[0],"speech":[1,10,27,33,54,76,98,104,120,129],"translation":[2,13,92,137],"(SST)":[3],"outputs":[4],"translations":[5],"in":[6],"parallel":[7],"with":[8,85],"streaming":[9,29,46],"input,":[11],"balancing":[12],"quality":[14],"and":[15,57,71,100],"latency.While":[16],"large":[17],"language":[18],"models":[19],"(LLMs)":[20],"have":[21],"been":[22],"extended":[23],"to":[24,62,81,114],"handle":[25],"the":[26,40,67,116,127,145],"modality,":[28],"remains":[30],"challenging":[31],"as":[32,36,150],"is":[34,112],"prepended":[35],"a":[37,59,106,135],"prompt":[38],"for":[39],"entire":[41],"generation":[42],"process.To":[43],"unlock":[44],"LLM":[45],"capability,":[47],"this":[48],"paper":[49],"proposes":[50],"SimulS2S-LLM,":[51],"which":[52],"trains":[53],"LLMs":[55],"offline":[56],"employs":[58],"test-time":[60],"policy":[61],"guide":[63],"simultaneous":[64,90],"inference.SimulS2S-LLM":[65],"alleviates":[66],"mismatch":[68],"between":[69],"training":[70,147],"inference":[72],"by":[73,94,154],"extracting":[74],"boundary-aware":[75],"prompts":[77],"that":[78,132,143],"allows":[79],"it":[80],"be":[82],"better":[83,136],"matched":[84],"text":[86],"input":[87],"data.SimulS2S-LLM":[88],"achieves":[89],"speech-to-speech":[91],"(Simul-S2ST)":[93],"predicting":[95],"discrete":[96],"output":[97,103],"tokens":[99],"then":[101],"synthesising":[102],"using":[105],"pretrained":[107],"vocoder.An":[108],"incremental":[109],"beam":[110],"search":[111,117],"designed":[113],"expand":[115],"space":[118],"of":[119],"token":[121],"prediction":[122],"without":[123],"increasing":[124],"latency.Experiments":[125],"on":[126],"CVSS":[128],"data":[130],"show":[131],"SimulS2S-LLM":[133],"offers":[134],"quality-latency":[138],"trade-off":[139],"than":[140],"existing":[141],"methods":[142],"use":[144],"same":[146],"data,":[148],"such":[149],"improving":[151],"ASR-BLEU":[152],"scores":[153],"3":[155],"points":[156],"at":[157],"similar":[158],"latency.":[159]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}