{"id":"https://openalex.org/W4405709756","doi":"https://doi.org/10.1109/iscslp63861.2024.10800488","title":"Enhancing Mispronunciation Detection with WavLM and Mixture-of-Experts Network","display_name":"Enhancing Mispronunciation Detection with WavLM and Mixture-of-Experts Network","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709756","doi":"https://doi.org/10.1109/iscslp63861.2024.10800488"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5104213271","display_name":"Wenqian Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenqian Bao","raw_affiliation_strings":["School of Information Science, Beijing Language and Culture University"],"affiliations":[{"raw_affiliation_string":"School of Information Science, Beijing Language and Culture University","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061263278","display_name":"Yuchen Yan","orcid":"https://orcid.org/0009-0005-8672-4468"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Yan","raw_affiliation_strings":["School of Information Science, Beijing Language and Culture University"],"affiliations":[{"raw_affiliation_string":"School of Information Science, Beijing Language and Culture University","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052176517","display_name":"Jinsong Zhang","orcid":"https://orcid.org/0000-0002-1603-3136"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinsong Zhang","raw_affiliation_strings":["School of Information Science, Beijing Language and Culture University"],"affiliations":[{"raw_affiliation_string":"School of Information Science, Beijing Language and Culture University","institution_ids":["https://openalex.org/I115212828"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5104213271"],"corresponding_institution_ids":["https://openalex.org/I115212828"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37860209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"189","last_page":"193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13274","display_name":"Expert finding and Q&A systems","score":0.9728000164031982,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13274","display_name":"Expert finding and Q&A systems","score":0.9728000164031982,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9707000255584717,"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/T13018","display_name":"Seismology and Earthquake Studies","score":0.9501000046730042,"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":0.6833208203315735},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39858704805374146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6833208203315735},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39858704805374146}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1635512741","https://openalex.org/W1982960403","https://openalex.org/W2072059109","https://openalex.org/W2077804127","https://openalex.org/W2150884987","https://openalex.org/W2552635739","https://openalex.org/W2794506738","https://openalex.org/W2888954148","https://openalex.org/W2916301830","https://openalex.org/W2962898354","https://openalex.org/W2972441390","https://openalex.org/W3081817774","https://openalex.org/W3198712976","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4226046739","https://openalex.org/W4253291564","https://openalex.org/W4296068419","https://openalex.org/W4385823283","https://openalex.org/W6732520560","https://openalex.org/W6780218876","https://openalex.org/W6788811087"],"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":{"Mispronunciation":[0],"Detection":[1],"and":[2,32,52,65,93,114,155],"Diagnosis":[3],"(MDD)":[4],"technologies":[5],"are":[6],"pivotal":[7],"elements":[8],"of":[9,26,34,47,55,68,106,134,167,173],"Computer-Assisted":[10],"Pronunciation":[11],"Training":[12],"(CAPT)":[13],"systems.":[14],"Despite":[15],"the":[16,24,30,45,53,59,73,83,121,131,157,171],"progress":[17],"in":[18,118,176],"deep":[19],"learning":[20],"that":[21,110],"has":[22],"enhanced":[23],"efficacy":[25,172],"pronunciation":[27,66],"error":[28,56],"detection,":[29],"capabilities":[31],"robustness":[33],"current":[35],"systems":[36],"must":[37],"be":[38],"further":[39],"augmented,":[40],"particularly":[41],"when":[42],"confronted":[43],"with":[44,120],"scarcity":[46],"second":[48],"language":[49],"(L2)":[50],"data":[51],"multitude":[54],"types.":[57],"Additionally,":[58],"mother":[60],"tongue":[61],"background,":[62],"age,":[63],"gender,":[64],"habits":[67],"L2":[69],"learners":[70],"significantly":[71],"influence":[72],"assessment":[74],"process.":[75],"Divergent":[76],"from":[77],"prior":[78],"endeavors,":[79],"this":[80],"study":[81],"leverages":[82],"Self-Supervised":[84],"Pretraining":[85],"(SSP)":[86],"model":[87],"WavLM":[88],"to":[89,98,130],"extract":[90],"acoustic":[91],"features":[92],"integrates":[94],"a":[95,104,126],"speaker":[96,123,153],"classifier":[97],"distill":[99],"L1-accent-related":[100],"features.":[101],"We":[102],"introduce":[103],"Mixture":[105],"Experts":[107],"(MoE)":[108],"system":[109,162],"dynamically":[111],"assigns":[112],"weights":[113],"selects":[115],"expert":[116],"models":[117],"accordance":[119],"extracted":[122],"information,":[124],"enabling":[125],"more":[127],"tailored":[128],"adaptation":[129],"phonetic":[132],"traits":[133],"individual":[135],"speakers.":[136],"Experiments":[137],"were":[138],"conducted":[139],"utilizing":[140],"two":[141],"publicly":[142],"accessible":[143],"datasets":[144],"(TIMIT,":[145],"L2-arctic),":[146],"demonstrating":[147],"consistent":[148],"performance":[149],"enhancement":[150],"across":[151],"various":[152],"profiles":[154],"bolstering":[156],"system's":[158],"robustness.":[159],"The":[160],"optimal":[161],"achieved":[163],"an":[164],"F1":[165],"score":[166],"78.48%,":[168],"thereby":[169],"substantiating":[170],"our":[174],"approach":[175],"MDD":[177],"applications.":[178]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}