{"id":"https://openalex.org/W7138233441","doi":"https://doi.org/10.1609/aaai.v40i36.40330","title":"Efficient and Adaptive Simultaneous Speech Translation with Fully Unidirectional Architecture","display_name":"Efficient and Adaptive Simultaneous Speech Translation with Fully Unidirectional Architecture","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138233441","doi":"https://doi.org/10.1609/aaai.v40i36.40330"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i36.40330","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i36.40330","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i36.40330","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129714458","display_name":"Biao Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Biao Fu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129716066","display_name":"Donglei Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Donglei Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073673415","display_name":"Minpeng Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minpeng Liao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129696616","display_name":"Chengxi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengxi Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123531514","display_name":"Xinjie Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinjie Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129689397","display_name":"Yidong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yidong Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129716371","display_name":"Kai Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126397121","display_name":"Xiaodong Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaodong Shi","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":21.2894,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97816257,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"40","issue":"36","first_page":"30735","last_page":"30743"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7817000150680542,"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":0.7817000150680542,"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":0.09279999881982803,"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":0.029100000858306885,"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/task","display_name":"Task (project management)","score":0.5982000231742859},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5698999762535095},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.525600016117096},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.5214999914169312},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5016999840736389},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4627000093460083},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.46059998869895935},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.39800000190734863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8327000141143799},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6139000058174133},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5982000231742859},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5698999762535095},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.525600016117096},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.5214999914169312},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5016999840736389},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4627000093460083},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.46059998869895935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45410001277923584},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42809998989105225},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.376800000667572},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3352000117301941},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30869999527931213},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i36.40330","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i36.40330","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i36.40330","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i36.40330","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Simultaneous":[0,70],"speech":[1,10,47,80],"translation":[2,23,139],"(SimulST)":[3],"produces":[4],"translations":[5],"incrementally":[6],"while":[7],"processing":[8],"partial":[9],"input.":[11],"Although":[12],"large":[13],"language":[14],"models":[15],"(LLMs)":[16],"have":[17],"shown":[18],"strong":[19,165],"capabilities":[20],"in":[21],"offline":[22],"tasks,":[24],"applying":[25],"them":[26],"to":[27,42,91,132,163],"SimulST":[28,34,95,100],"poses":[29],"notable":[30],"challenges.":[31],"Existing":[32],"LLM-based":[33],"approaches":[35],"either":[36],"incur":[37],"significant":[38],"computational":[39],"overhead":[40],"due":[41],"repeated":[43],"encoding":[44],"of":[45],"bidirectional":[46],"encoder,":[48],"or":[49],"they":[50],"depend":[51],"on":[52,144],"a":[53,86,116,128],"fixed":[54],"read/write":[55,108,123],"policy,":[56],"limiting":[57],"the":[58],"efficiency":[59],"and":[60,68,82,98,136,140,148,152],"performance.":[61],"In":[62],"this":[63],"work,":[64],"we":[65,114,126],"introduce":[66],"Efficient":[67],"Adaptive":[69],"Speech":[71],"Translation":[72],"(EASiST)":[73],"with":[74,106],"fully":[75],"unidirectional":[76],"architecture,":[77],"including":[78],"both":[79,138,145],"encoder":[81],"LLM.":[83],"EASiST":[84,157],"includes":[85],"multi-latency":[87],"data":[88],"curation":[89],"strategy":[90,131],"generate":[92],"semantically":[93],"aligned":[94],"training":[96,130],"samples":[97],"redefines":[99],"as":[101],"an":[102],"interleaved":[103],"generation":[104],"task":[105],"explicit":[107],"tokens.":[109],"To":[110],"facilitate":[111],"adaptive":[112],"inference,":[113],"incorporate":[115],"lightweight":[117],"policy":[118,141],"head":[119],"that":[120,156],"dynamically":[121],"predicts":[122],"actions.":[124],"Additionally,":[125],"employ":[127],"multi-stage":[129],"align":[133],"speech-text":[134],"modalities":[135],"optimize":[137],"behavior.":[142],"Experiments":[143],"in-domain":[146],"(MuST-C)":[147],"out-of-domain":[149],"(Europarl-ST)":[150],"En-De":[151],"En-Es":[153],"datasets":[154],"demonstrate":[155],"offers":[158],"superior":[159],"latency-quality":[160],"trade-offs":[161],"compared":[162],"several":[164],"baselines.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}