{"id":"https://openalex.org/W7166881359","doi":"https://doi.org/10.18653/v1/2026.acl-long.1634","title":"LCMA-SRT: Language-Conditional Mixture-of-Experts Adapters for Joint Multilingual Speech Recognition and Translation","display_name":"LCMA-SRT: Language-Conditional Mixture-of-Experts Adapters for Joint Multilingual Speech Recognition and Translation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166881359","doi":"https://doi.org/10.18653/v1/2026.acl-long.1634"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1634","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1634","pdf_url":"https://aclanthology.org/2026.acl-long.1634.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 64th 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/2026.acl-long.1634.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121162906","display_name":"Nanjie Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116494","display_name":"Timber Institute","ror":"https://ror.org/02phgvp38","country_code":"CZ","type":"other","lineage":["https://openalex.org/I4210116494"]},{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN","CZ"],"is_corresponding":false,"raw_author_name":"Nanjie Li","raw_affiliation_strings":["School of Computer Science and Technology , Xinjiang University , Urumqi , China","Timekettle AI Lab , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , Xinjiang University , Urumqi , China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Timekettle AI Lab , Shenzhen , China","institution_ids":["https://openalex.org/I4210116494"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139741032","display_name":"Xiaoyong Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116494","display_name":"Timber Institute","ror":"https://ror.org/02phgvp38","country_code":"CZ","type":"other","lineage":["https://openalex.org/I4210116494"]},{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN","CZ"],"is_corresponding":false,"raw_author_name":"Xiaoyong Guo","raw_affiliation_strings":["School of Computer Science and Technology , Xinjiang University , Urumqi , China","Timekettle AI Lab , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , Xinjiang University , Urumqi , China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Timekettle AI Lab , Shenzhen , China","institution_ids":["https://openalex.org/I4210116494"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139797560","display_name":"Hao Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I1322829787","display_name":"SIL Global","ror":"https://ror.org/00d57b563","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1322829787"]},{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["Joint International Research Laboratory of Silk Road Multilingual Cognitive Computing , Urumqi , China","School of Computer Science and Technology , Xinjiang University , Urumqi , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Joint International Research Laboratory of Silk Road Multilingual Cognitive Computing , Urumqi , China","institution_ids":["https://openalex.org/I1322829787"]},{"raw_affiliation_string":"School of Computer Science and Technology , Xinjiang University , Urumqi , China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139736059","display_name":"Xu Haihua","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116494","display_name":"Timber Institute","ror":"https://ror.org/02phgvp38","country_code":"CZ","type":"other","lineage":["https://openalex.org/I4210116494"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Xu Haihua","raw_affiliation_strings":["Timekettle AI Lab , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Timekettle AI Lab , Shenzhen , China","institution_ids":["https://openalex.org/I4210116494"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139748765","display_name":"Wei Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116494","display_name":"Timber Institute","ror":"https://ror.org/02phgvp38","country_code":"CZ","type":"other","lineage":["https://openalex.org/I4210116494"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Wei Shi","raw_affiliation_strings":["Timekettle AI Lab , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Timekettle AI Lab , Shenzhen , China","institution_ids":["https://openalex.org/I4210116494"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83899568,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"35363","last_page":"35377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8133000135421753,"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":0.8133000135421753,"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":0.02250000089406967,"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/T12031","display_name":"Speech and dialogue systems","score":0.017799999564886093,"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/joint","display_name":"Joint (building)","score":0.7052000164985657},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.45159998536109924},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.39410001039505005},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3095000088214874},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.25119999051094055}],"concepts":[{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7052000164985657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.666100025177002},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5871999859809875},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.45159998536109924},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42309999465942383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4068000018596649},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2433999925851822}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1634","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1634","pdf_url":"https://aclanthology.org/2026.acl-long.1634.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1634","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1634","pdf_url":"https://aclanthology.org/2026.acl-long.1634.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2513669990","display_name":null,"funder_award_id":"62466055","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166881359.pdf","grobid_xml":"https://content.openalex.org/works/W7166881359.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Neural":[0],"transducers":[1,38],"offer":[2],"an":[3,33],"alignment-free":[4],"framework":[5],"for":[6,61,72],"speech-to-text":[7],"modeling,":[8],"and":[9,21,53,75,98,115,134,144,147,157],"hierarchical":[10,37,80,151],"transducer":[11,81,152],"architectures":[12],"further":[13],"improve":[14,99],"multilingual":[15,40,100],"joint":[16,139],"automatic":[17],"speech":[18,22],"recognition":[19],"(ASR)":[20],"translation":[23],"(ST)":[24],"by":[25],"stacking":[26],"a":[27,79,137],"translation-focused":[28],"encoder":[29],"on":[30,122],"top":[31],"of":[32],"ASR":[34,133],"encoder.However,":[35],"extending":[36],"to":[39,94,111],"manyto-many":[41],"settings":[42],"remains":[43],"challenging:":[44],"fully":[45],"shared":[46],"models":[47,60,158],"often":[48],"suffer":[49],"from":[50],"negative":[51],"transfer":[52],"unstable":[54],"target-language":[55],"generation,":[56],"while":[57],"training":[58],"separate":[59],"each":[62],"direction":[63],"is":[64],"computationally":[65],"prohibitive.We":[66],"propose":[67],"LCMA-SRT":[68,130],"(Language-Conditional":[69],"Mixtureof-Experts":[70],"Adapters":[71],"Speech":[73],"Recognition":[74],"Translation),":[76],"which":[77],"augments":[78],"with":[82],"language-conditional":[83],"Mixture-of-Experts":[84],"(MoE)":[85],"adapters.A":[86],"sourceconditioned":[87],"MoE":[88,103],"adapter":[89,104],"(SRC-MoE)":[90],"uses":[91,106],"source-language":[92],"embeddings":[93],"reduce":[95,112],"crosslanguage":[96],"interference":[97,114],"ASR.A":[101],"target-conditioned":[102],"(TGT-MoE)":[105],"the":[107],"desired":[108],"target":[109],"language":[110],"cross-target":[113],"stabilize":[116],"targetlanguage":[117],"generation":[118],"in":[119],"many-to-many":[120],"ST.Experiments":[121],"Europarl-ST":[123],"(9":[124],"languages,":[125],"72":[126],"directions)":[127],"show":[128],"that":[129],"improves":[131],"both":[132],"ST":[135],"within":[136],"single":[138],"model,":[140],"reducing":[141],"average":[142],"WER":[143],"improving":[145],"BLEU":[146],"COMET":[148],"over":[149],"strong":[150],"baselines.We":[153],"release":[154],"our":[155],"code":[156],"at":[159],"https://github.com/linanjie0820/":[160],"LCMA-SRT.":[161]},"counts_by_year":[],"updated_date":"2026-08-27T14:10:00.468798","created_date":"2026-07-02T00:00:00"}
