{"id":"https://openalex.org/W4402352982","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651105","title":"MoNet: A Mixture of Experts Solution for Multilingual and Low-Resource ASR Challenges","display_name":"MoNet: A Mixture of Experts Solution for Multilingual and Low-Resource ASR Challenges","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352982","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651105"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10651105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10651105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","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/A5101806000","display_name":"Yongchao Li","orcid":"https://orcid.org/0000-0002-4460-9702"},"institutions":[{"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"],"is_corresponding":true,"raw_author_name":"Yongchao Li","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China,830046"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830046","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057973134","display_name":"Lixu Sun","orcid":"https://orcid.org/0000-0002-3609-6636"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Lixu Sun","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China,830046"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830046","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114207576","display_name":"Yineng Cai","orcid":null},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Yineng Cai","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China,830046"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830046","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076021252","display_name":"Nurmemet Yolwas","orcid":null},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Nurmemet Yolwas","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China,830046"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830046","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101806000"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":0.6891,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75446015,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9962999820709229,"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/T10028","display_name":"Topic Modeling","score":0.9947999715805054,"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":0.6685018539428711},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.6345689296722412},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3247072100639343},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32373493909835815},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10825449228286743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6685018539428711},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.6345689296722412},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3247072100639343},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32373493909835815},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10825449228286743}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10651105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10651105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.4399999976158142,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2022638422","https://openalex.org/W2125838338","https://openalex.org/W2127141656","https://openalex.org/W2144499799","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2936774411","https://openalex.org/W2963292011","https://openalex.org/W3030437843","https://openalex.org/W3097777922","https://openalex.org/W3197478142","https://openalex.org/W3197813307","https://openalex.org/W3202136075","https://openalex.org/W3203140070","https://openalex.org/W3215427016","https://openalex.org/W4206375145","https://openalex.org/W4225615476","https://openalex.org/W4281395113","https://openalex.org/W4281779489","https://openalex.org/W4287391717","https://openalex.org/W4293718192","https://openalex.org/W4323066695","https://openalex.org/W4378105483","https://openalex.org/W4385245566","https://openalex.org/W4385823078","https://openalex.org/W4388017359","https://openalex.org/W4394652872","https://openalex.org/W6732520560","https://openalex.org/W6751779834","https://openalex.org/W6771467084","https://openalex.org/W6788811087","https://openalex.org/W6802010262","https://openalex.org/W6810321870","https://openalex.org/W6838276489","https://openalex.org/W6847363464","https://openalex.org/W6850218400","https://openalex.org/W6852909395","https://openalex.org/W6863725965"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Contemporary":[0],"end-to-end":[1],"automatic":[2,69],"speech":[3,70,91,258],"recognition":[4,71,259],"models":[5,48],"have":[6],"demonstrated":[7],"remarkable":[8],"performance":[9],"in":[10,22,175,208,226],"monolingual":[11],"contexts":[12],"with":[13,172,204],"abundant":[14],"corpora.":[15],"However,":[16],"their":[17],"efficacy":[18],"is":[19,83],"considerably":[20],"compromised":[21],"multilingual":[23,68,90,257],"and":[24,87,126,138,156,183,220],"resource-scarce":[25],"environments":[26],"due":[27],"to":[28,32,49,109,121,146,196,215,238],"the":[29,35,76,94,103,123,132,139,149,159,186,197,241,248],"models\u2019":[30],"inability":[31],"effectively":[33],"learn":[34],"diverse":[36,170],"linguistic":[37],"features":[38,56],"from":[39,117,167,185],"unevenly":[40],"distributed":[41],"corpora":[42,166],"during":[43],"training.":[44],"Hence,":[45],"enabling":[46],"these":[47],"assimilate":[50],"a":[51,58,66,107,111,142,163,205],"broader":[52],"spectrum":[53],"of":[54,78,85,114,134,141,158,165,213,224,240,251],"effective":[55],"presents":[57],"significant":[59,202,249],"challenge.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64],"introduce":[65],"novel":[67],"network,":[72],"MoNet,":[73,102],"predicated":[74],"on":[75],"Mixture":[77],"Experts":[79],"(MoE)":[80],"approach,":[81],"which":[82],"capable":[84],"automatically":[86],"efficiently":[88],"processing":[89],"data":[92],"without":[93],"need":[95],"for":[96,217,255],"any":[97],"language-specific":[98],"cues.":[99],"Specifically,":[100],"within":[101],"MoE":[104],"layer":[105],"employs":[106],"router":[108],"select":[110],"fixed":[112],"number":[113],"optimal":[115],"experts":[116],"an":[118,221,234],"expert":[119],"pool":[120],"guide":[122],"network\u2019s":[124],"learning":[125],"provide":[127],"efficacious":[128],"reasoning,":[129],"followed":[130],"by":[131],"use":[133],"joint":[135],"CTC/Attention":[136],"training":[137,155,177],"implementation":[140],"secondary":[143],"scoring":[144],"mechanism":[145],"further":[147],"enhance":[148],"model\u2019s":[150],"performance.":[151],"We":[152],"conducted":[153],"hybrid":[154],"evaluation":[157],"proposed":[160,253],"model":[161,254],"using":[162],"compendium":[164],"six":[168],"linguistically":[169],"languages":[171,219],"considerable":[173],"variance":[174],"total":[176],"duration\u2014Turkish,":[178],"Uighur,":[179],"Bashkir,":[180],"Uzbek,":[181],"Kyrgyz,":[182],"Russian\u2014sourced":[184],"publicly":[187],"accessible":[188],"CommonVoice":[189],"dataset.":[190],"Our":[191],"findings":[192],"indicate":[193],"that":[194,239],"compared":[195],"baseline":[198,242],"model,":[199],"MoNet":[200],"achieves":[201],"improvements,":[203],"maximum":[206],"reduction":[207],"Word":[209],"Error":[210],"Rate":[211],"(WER)":[212],"up":[214],"4.1%":[216],"individual":[218],"average":[222],"decrease":[223],"1.78%":[225],"WER":[227],"across":[228],"multiple":[229],"languages,":[230],"while":[231],"still":[232],"maintaining":[233],"inference":[235],"cost":[236],"comparable":[237],"model.":[243],"The":[244],"experimental":[245],"outcomes":[246],"underscore":[247],"advantages":[250],"our":[252],"low-resource,":[256],"tasks.":[260]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}