{"id":"https://openalex.org/W4408352822","doi":"https://doi.org/10.1109/icassp49660.2025.10890805","title":"Dynamic Language Group-based MoE: Enhancing Code-Switching Speech Recognition with Hierarchical Routing","display_name":"Dynamic Language Group-based MoE: Enhancing Code-Switching Speech Recognition with Hierarchical Routing","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352822","doi":"https://doi.org/10.1109/icassp49660.2025.10890805"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890805","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890805","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109692702","display_name":"Hukai Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hukai Huang","raw_affiliation_strings":["Xiamen University,School of Informatics,Xiamen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111310820","display_name":"Shenghui Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenghui Lu","raw_affiliation_strings":["Xiamen University,School of Informatics,Xiamen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022676888","display_name":"Yahui Shan","orcid":"https://orcid.org/0000-0002-1510-2590"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]},{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yahui Shan","raw_affiliation_strings":["Kuaishou Technology Co., Ltd,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co., Ltd,Beijing,China","institution_ids":["https://openalex.org/I4210155967","https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101319176","display_name":"He Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]},{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Qu","raw_affiliation_strings":["Kuaishou Technology Co., Ltd,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co., Ltd,Beijing,China","institution_ids":["https://openalex.org/I4210155967","https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027555657","display_name":"Fengrun Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]},{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengrun Zhang","raw_affiliation_strings":["Kuaishou Technology Co., Ltd,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co., Ltd,Beijing,China","institution_ids":["https://openalex.org/I4210155967","https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111310824","display_name":"Wenhao Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Guan","raw_affiliation_strings":["Xiamen University,School of Informatics,Xiamen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011997254","display_name":"Qingyang Hong","orcid":"https://orcid.org/0000-0001-7380-8690"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Hong","raw_affiliation_strings":["Xiamen University,School of Informatics,Xiamen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100412926","display_name":"Lin Li","orcid":"https://orcid.org/0000-0003-0426-6546"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Xiamen University,School of Electronic Science and Engineering,Xiamen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Engineering,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9860000014305115,"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":0.9860000014305115,"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/T12031","display_name":"Speech and dialogue systems","score":0.9689000248908997,"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/computer-science","display_name":"Computer science","score":0.7602471113204956},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5214897394180298},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.46550920605659485},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45337599515914917},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2523261308670044},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2436540424823761}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7602471113204956},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5214897394180298},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.46550920605659485},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45337599515914917},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2523261308670044},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2436540424823761},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890805","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890805","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2892009249","https://openalex.org/W3096032230","https://openalex.org/W3096122506","https://openalex.org/W3097777922","https://openalex.org/W3156323585","https://openalex.org/W3215427016","https://openalex.org/W4221167707","https://openalex.org/W4281770669","https://openalex.org/W4297841441","https://openalex.org/W4297841499","https://openalex.org/W4372269995","https://openalex.org/W4372349677","https://openalex.org/W4375869049","https://openalex.org/W4385822813","https://openalex.org/W4385822875","https://openalex.org/W4385823078","https://openalex.org/W4385823213","https://openalex.org/W4391021741","https://openalex.org/W4392902746","https://openalex.org/W4392903651","https://openalex.org/W4392904635","https://openalex.org/W4406461663","https://openalex.org/W6732520560","https://openalex.org/W6780805062","https://openalex.org/W6780815891","https://openalex.org/W6788811087","https://openalex.org/W6865554915"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"Mixture":[1],"of":[2,30,56],"Experts":[3],"(MoE)":[4],"model":[5,131],"is":[6],"a":[7,40,63,136],"promising":[8],"approach":[9],"for":[10],"handling":[11],"code-switching":[12],"speech":[13],"recognition":[14],"(CS-ASR)":[15],"tasks.":[16],"However,":[17],"the":[18,28,49,54,68,73,78,81,87,107,130],"existing":[19,108],"CS-ASR":[20,50,112],"work":[21,37],"on":[22,62,111],"MoE":[23,109],"has":[24],"yet":[25],"to":[26,80,134],"leverage":[27,53],"advantages":[29,55],"MoE\u2019s":[31],"parameter":[32,57],"scaling":[33],"ability":[34],"fully.":[35],"This":[36],"proposes":[38],"DLG-MoE,":[39],"Dynamic":[41],"Language":[42],"Group-based":[43],"MoE,":[44],"which":[45],"can":[46,127],"effectively":[47],"handle":[48],"task":[51],"and":[52,76,99,103,123,126],"scaling.":[58],"DLG-MoE":[59,105],"operates":[60],"based":[61],"hierarchical":[64],"routing":[65,102],"mechanism.":[66],"First,":[67],"language":[69,74,83,92,98],"router":[70,89],"explicitly":[71],"models":[72,95],"attribute":[75],"dispatches":[77],"representations":[79],"corresponding":[82],"expert":[84,101],"groups.":[85],"Subsequently,":[86],"unsupervised":[88],"within":[90],"each":[91],"group":[93],"implicitly":[94],"attributes":[96],"beyond":[97],"coordinates":[100],"collaboration.":[104],"outperforms":[106],"methods":[110],"tasks":[113],"while":[114],"demonstrating":[115],"great":[116],"flexibility.":[117],"It":[118],"supports":[119],"different":[120],"top-k":[121],"inference":[122],"streaming":[124],"capabilities":[125],"also":[128],"prune":[129],"parameters":[132],"flexibly":[133],"obtain":[135],"monolingual":[137],"sub-model.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
