{"id":"https://openalex.org/W7082654557","doi":"https://doi.org/10.3724/2096-7004.di.2025.0139","title":"Dynamic Language Routing Mixture of Experts Model for Multilingual Speech Recognition","display_name":"Dynamic Language Routing Mixture of Experts Model for Multilingual Speech Recognition","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W7082654557","doi":"https://doi.org/10.3724/2096-7004.di.2025.0139"},"language":"en","primary_location":{"id":"doi:10.3724/2096-7004.di.2025.0139","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0139","pdf_url":"https://www.sciengine.com/doi/pdf/297C19FDBE634578A55F03DC2B625B4F","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.sciengine.com/doi/pdf/297C19FDBE634578A55F03DC2B625B4F","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Junchen Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junchen Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yonghe Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yonghe Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Feilong Bao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feilong Bao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Guanglai Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guanglai Gao","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.63238707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"2","first_page":"20250139","last_page":"20250139"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6664000153541565,"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/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6664000153541565,"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/T13067","display_name":"Geological Modeling and Analysis","score":0.02800000086426735,"subfield":{"id":"https://openalex.org/subfields/1906","display_name":"Geochemistry and Petrology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14311","display_name":"Electrical and Electromagnetic Research","score":0.01720000058412552,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/subnetwork","display_name":"Subnetwork","score":0.758400022983551},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.6830999851226807},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5332000255584717},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.4453999996185303},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.40130001306533813},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36739999055862427},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.36079999804496765},{"id":"https://openalex.org/keywords/adaptive-routing","display_name":"Adaptive routing","score":0.3531000018119812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8345000147819519},{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.758400022983551},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6830999851226807},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5781000256538391},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5332000255584717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46950000524520874},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.4453999996185303},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4426000118255615},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C24856439","wikidata":"https://www.wikidata.org/wiki/Q352483","display_name":"Adaptive routing","level":5,"score":0.3531000018119812},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2992999851703644},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28139999508857727},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.27160000801086426},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.2581000030040741},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3724/2096-7004.di.2025.0139","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0139","pdf_url":"https://www.sciengine.com/doi/pdf/297C19FDBE634578A55F03DC2B625B4F","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3724/2096-7004.di.2025.0139","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0139","pdf_url":"https://www.sciengine.com/doi/pdf/297C19FDBE634578A55F03DC2B625B4F","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7082654557.pdf","grobid_xml":"https://content.openalex.org/works/W7082654557.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multilingual":[0],"Automatic":[1],"Speech":[2],"Recognition":[3],"(MASR)":[4],"systems":[5],"have":[6],"inherent":[7],"difficulties":[8],"in":[9,66,108],"balancing":[10],"computational":[11],"efficiency":[12],"and":[13,58,123],"modeling":[14],"phonetic":[15,71],"similarities":[16,72],"between":[17,73],"different":[18,74],"languages.":[19],"This":[20,40],"study":[21],"proposes":[22,78],"a":[23,28,34,79],"MASR":[24],"framework":[25,94],"based":[26,48],"on":[27,49],"Mixture-of-Experts":[29],"(MoE)":[30],"architecture,":[31],"which":[32],"incorporates":[33],"dynamic":[35],"Top-<italic>k</italic>":[36],"expert":[37,46,67,90],"routing":[38],"strategy.":[39],"method":[41,83],"dynamically":[42],"selects":[43],"the":[44,50,64,93,98],"optimal":[45],"subnetwork":[47],"input":[51],"speech":[52],"features,":[53],"thereby":[54],"achieving":[55],"more":[56],"efficient":[57],"accurate":[59],"language":[60,87],"modeling.":[61],"To":[62],"address":[63],"ambiguity":[65],"selection":[68],"caused":[69],"by":[70],"languages,":[75],"we":[76],"further":[77],"<italic>Token-Level":[80],"Realignment</italic>":[81],"(TLR)":[82],"that":[84],"accurately":[85],"aligns":[86],"representations":[88],"with":[89,117],"groups":[91],"at":[92],"level,":[95],"effectively":[96],"alleviating":[97],"cross-language":[99],"interference":[100],"problem.":[101],"The":[102],"experiments":[103],"achieved":[104],"excellent":[105],"recognition":[106],"performance":[107],"four":[109],"languages":[110],"(English,":[111],"Chinese,":[112],"Khalkha":[113],"Mongolian,":[114],"Chahar":[115],"Mongolian),":[116],"WERs/CERs":[118],"of":[119],"12.88%,":[120],"5.49%,":[121],"7.64%,":[122],"19.30%,":[124],"respectively.":[125]},"counts_by_year":[],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2025-10-10T00:00:00"}