{"id":"https://openalex.org/W4391021741","doi":"https://doi.org/10.1109/asru57964.2023.10389798","title":"BA-MoE: Boundary-Aware Mixture-of-Experts Adapter for Code-Switching Speech Recognition","display_name":"BA-MoE: Boundary-Aware Mixture-of-Experts Adapter for Code-Switching Speech Recognition","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021741","doi":"https://doi.org/10.1109/asru57964.2023.10389798"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5085355820","display_name":"Peikun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peikun Chen","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100616400","display_name":"Fan Yu","orcid":"https://orcid.org/0000-0002-0576-7396"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yu","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102543677","display_name":"Yuhao Liang","orcid":"https://orcid.org/0009-0008-9516-6594"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Liang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014632942","display_name":"Hongfei Xue","orcid":"https://orcid.org/0000-0001-9691-9668"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongfei Xue","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047201304","display_name":"Xucheng Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xucheng Wan","raw_affiliation_strings":["Huawei Technologies,IT Innovation and Research Center","IT Innovation and Research Center, Huawei Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies,IT Innovation and Research Center","institution_ids":["https://openalex.org/I4210123571"]},{"raw_affiliation_string":"IT Innovation and Research Center, Huawei Technologies","institution_ids":["https://openalex.org/I4210123571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077304193","display_name":"Naijun Zheng","orcid":"https://orcid.org/0000-0001-8321-5418"},"institutions":[{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Naijun Zheng","raw_affiliation_strings":["Huawei Technologies,IT Innovation and Research Center","IT Innovation and Research Center, Huawei Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies,IT Innovation and Research Center","institution_ids":["https://openalex.org/I4210123571"]},{"raw_affiliation_string":"IT Innovation and Research Center, Huawei Technologies","institution_ids":["https://openalex.org/I4210123571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084727631","display_name":"Huan Zhou","orcid":"https://orcid.org/0000-0003-2319-4103"},"institutions":[{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Huan Zhou","raw_affiliation_strings":["Huawei Technologies,IT Innovation and Research Center","IT Innovation and Research Center, Huawei Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies,IT Innovation and Research Center","institution_ids":["https://openalex.org/I4210123571"]},{"raw_affiliation_string":"IT Innovation and Research Center, Huawei Technologies","institution_ids":["https://openalex.org/I4210123571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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":0.9968000054359436,"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/adapter","display_name":"Adapter (computing)","score":0.8596956729888916},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6611934900283813},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6236358880996704},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.4481484293937683},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17622700333595276},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10844609141349792}],"concepts":[{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.8596956729888916},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6611934900283813},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6236358880996704},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4481484293937683},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17622700333595276},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10844609141349792},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2091715339","https://openalex.org/W2194775991","https://openalex.org/W2889519245","https://openalex.org/W2939069254","https://openalex.org/W2964156075","https://openalex.org/W2972324550","https://openalex.org/W3016167541","https://openalex.org/W3042170933","https://openalex.org/W3096122506","https://openalex.org/W3097306574","https://openalex.org/W3097777922","https://openalex.org/W3160201895","https://openalex.org/W3165404421","https://openalex.org/W3217003515","https://openalex.org/W4225644313","https://openalex.org/W4281770669","https://openalex.org/W4285070019","https://openalex.org/W4288408927","https://openalex.org/W4297841499","https://openalex.org/W4308167208","https://openalex.org/W4372269995","https://openalex.org/W4380136693","https://openalex.org/W4388017359","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6735377749","https://openalex.org/W6739901393","https://openalex.org/W6760937267","https://openalex.org/W6780815891","https://openalex.org/W6809686867","https://openalex.org/W6839144119","https://openalex.org/W6847070983","https://openalex.org/W6853581730"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2133028525","https://openalex.org/W4229060448","https://openalex.org/W4306381730","https://openalex.org/W2981692913","https://openalex.org/W3044188621","https://openalex.org/W3184035966","https://openalex.org/W2160602540","https://openalex.org/W2485605994"],"abstract_inverted_index":{"Mixture-of-experts":[0],"based":[1],"models,":[2],"which":[3],"use":[4],"language":[5,42,53,88,120],"experts":[6],"to":[7,27,69,78,99,113,137],"extract":[8],"language-specific":[9,67,71,97,104],"representations":[10,72,80,116],"effectively,":[11],"have":[12],"been":[13],"well":[14],"applied":[15],"in":[16,36],"code-switching":[17,145],"automatic":[18],"speech":[19],"recognition.":[20],"However,":[21],"there":[22],"is":[23],"still":[24],"substantial":[25],"space":[26],"improve":[28,100],"as":[29],"similar":[30],"pronunciation":[31],"across":[32],"languages":[33],"may":[34],"result":[35],"ineffective":[37],"multi-language":[38],"modeling":[39],"and":[40,55,73],"inaccurate":[41],"boundary":[43,115,121],"estimation.":[44],"To":[45],"eliminate":[46],"these":[47],"drawbacks,":[48],"we":[49,65,86,108],"propose":[50],"a":[51,56,74,110],"cross-layer":[52],"adapter":[54,98,102],"boundary-aware":[57,111],"training":[58],"method,":[59],"namely":[60],"Boundary-Aware":[61],"Mixture-of-Experts":[62],"(BA-MoE).":[63],"Specifically,":[64],"introduce":[66],"adapters":[68],"separate":[70],"unified":[75],"gating":[76],"layer":[77],"fuse":[79],"within":[81],"each":[82,96],"encoder":[83],"layer.":[84],"Second,":[85],"compute":[87],"adaptation":[89],"loss":[90],"of":[91,95],"the":[92,101,130,138,141],"mean":[93],"output":[94],"module\u2019s":[103],"representation":[105],"learning.":[106],"Besides,":[107],"utilize":[109],"predictor":[112],"learn":[114],"for":[117],"dealing":[118],"with":[119],"confusion.":[122],"Our":[123],"approach":[124],"achieves":[125],"significant":[126],"performance":[127],"improvement,":[128],"reducing":[129],"mixture":[131],"error":[132],"rate":[133],"by":[134],"16.55%":[135],"compared":[136],"baseline":[139],"on":[140],"ASRU":[142],"2019":[143],"Mandarin-English":[144],"challenge":[146],"dataset.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}