{"id":"https://openalex.org/W7137995915","doi":"https://doi.org/10.1609/aaai.v40i37.40360","title":"REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation","display_name":"REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137995915","doi":"https://doi.org/10.1609/aaai.v40i37.40360"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i37.40360","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i37.40360","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i37.40360","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099173854","display_name":"Nameer Hirschkind","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nameer Hirschkind","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129748922","display_name":"Joseph Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joseph Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129700061","display_name":"Xiao Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081255157","display_name":"Mahesh Kumar Nandwana","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahesh Kumar Nandwana","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5099173854"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20813269,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"37","first_page":"31005","last_page":"31013"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.4927000105381012,"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":0.4927000105381012,"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":0.13279999792575836,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.054499998688697815,"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":0.7006999850273132},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5238999724388123},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4823000133037567},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.46700000762939453},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4129999876022339},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.40849998593330383},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.36039999127388},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.3573000133037567}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900999784469604},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7006999850273132},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5238999724388123},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4984999895095825},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4823000133037567},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.46700000762939453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43630000948905945},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3027999997138977},{"id":"https://openalex.org/C2988416141","wikidata":"https://www.wikidata.org/wiki/Q6031139","display_name":"Information loss","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i37.40360","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i37.40360","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.v40i37.40360","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i37.40360","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Simultaneous":[0],"Speech":[1],"Translation":[2],"(SimulST)":[3],"systems":[4,16],"stream":[5],"in":[6],"audio":[7],"while":[8],"simultaneously":[9],"emitting":[10],"translated":[11],"text":[12],"or":[13,118],"speech.":[14],"Such":[15],"face":[17],"the":[18,85,90,145],"significant":[19],"challenge":[20],"of":[21,89,130],"balancing":[22],"translation":[23,70],"quality":[24],"and":[25,79,106,110],"latency.":[26],"We":[27,72,133],"introduce":[28,135],"a":[29,58,100,136],"strategy":[30],"to":[31,61,155],"optimize":[32],"this":[33,49],"tradeoff:":[34],"wait":[35],"for":[36,128,138],"more":[37],"input":[38],"only":[39,115],"if":[40],"you":[41],"gain":[42],"information":[43,76],"by":[44,148],"doing":[45],"so.":[46],"Based":[47],"on":[48,103,114],"strategy,":[50],"we":[51,98,122],"present":[52],"Regularized":[53],"Entropy":[54],"INformation":[55],"Adaptation":[56],"(REINA),":[57],"novel":[59],"loss":[60],"train":[62,99],"an":[63,67],"adaptive":[64],"policy":[65],"using":[66],"existing":[68],"non-streaming":[69,160],"model.":[71],"derive":[73],"REINA":[74,82,143],"from":[75,109],"theory":[77],"principles":[78],"show":[80],"that":[81],"helps":[83],"push":[84],"reported":[86],"Pareto":[87],"frontier":[88],"latency/quality":[91,146],"tradeoff":[92],"over":[93],"prior":[94,156],"works.":[95],"Utilizing":[96],"REINA,":[97],"SimulST":[101],"model":[102],"French,":[104],"Spanish":[105],"German,":[107],"both":[108],"into":[111],"English.":[112],"Training":[113],"open":[116],"source":[117],"synthetically":[119],"generated":[120],"data,":[121],"achieve":[123],"state-of-the-art":[124],"(SOTA)":[125],"streaming":[126,139],"results":[127],"models":[129],"comparable":[131],"size.":[132],"also":[134],"metric":[137],"efficiency,":[140],"quantitatively":[141],"showing":[142],"improves":[144],"trade-off":[147],"as":[149,151],"much":[150],"21":[152],"percent":[153],"compared":[154],"approaches,":[157],"normalized":[158],"against":[159],"baseline":[161],"BLEU":[162],"scores.":[163]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}