{"id":"https://openalex.org/W4408353580","doi":"https://doi.org/10.1109/icassp49660.2025.10887601","title":"Integrating Potential Pronunciations for Enhanced Mispronunciation Detection and Diagnosis Ability in LLMs","display_name":"Integrating Potential Pronunciations for Enhanced Mispronunciation Detection and Diagnosis Ability in LLMs","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353580","doi":"https://doi.org/10.1109/icassp49660.2025.10887601"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887601","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/A5101384220","display_name":"Minglin Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Minglin Wu","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026304746","display_name":"Jing Xu","orcid":"https://orcid.org/0000-0001-6257-8770"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jing Xu","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056333941","display_name":"X. R. Chen","orcid":"https://orcid.org/0000-0002-1660-5325"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xueyuan Chen","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79092198,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9639999866485596,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9639999866485596,"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":0.6562928557395935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3663938045501709},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34972378611564636}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6562928557395935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3663938045501709},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34972378611564636}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887601","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/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1985084205","https://openalex.org/W2054441760","https://openalex.org/W2127141656","https://openalex.org/W2139008940","https://openalex.org/W2402640444","https://openalex.org/W2768986418","https://openalex.org/W2938359332","https://openalex.org/W2972347929","https://openalex.org/W2979826702","https://openalex.org/W3015231007","https://openalex.org/W3196525293","https://openalex.org/W3197816268","https://openalex.org/W3198712976","https://openalex.org/W3209059054","https://openalex.org/W4297841567","https://openalex.org/W4386071707","https://openalex.org/W4389524500","https://openalex.org/W4392902938","https://openalex.org/W4392903956","https://openalex.org/W4392904020","https://openalex.org/W4393178509","https://openalex.org/W4402112136","https://openalex.org/W6780218876","https://openalex.org/W6796581206","https://openalex.org/W6810081322","https://openalex.org/W6850503672","https://openalex.org/W6850625674","https://openalex.org/W6852447913","https://openalex.org/W6860041859","https://openalex.org/W6861626678"],"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/W3204019825"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"exhibited":[5],"significant":[6],"potentials":[7],"across":[8],"various":[9],"tasks.":[10],"However,":[11],"how":[12],"to":[13,51,107],"leverage":[14],"the":[15,20,46,53,64,84,88,102,109,113,134],"power":[16],"of":[17,49,56,70,136],"LLMs":[18,57],"in":[19,58,112,128],"mispronunciation":[21],"detection":[22],"and":[23,77,91,96],"diagnosis":[24],"(MDD)":[25],"task":[26],"is":[27,68,105],"still":[28],"under-explored.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33],"propose":[34],"a":[35],"PP-ATP":[36,66,121],"model,":[37],"which":[38],"integrates":[39],"potential":[40,97,137],"pronunciations":[41,98],"covering":[42],"common":[43],"mispronunciations":[44],"into":[45],"prompt":[47,90],"part":[48],"LLMs,":[50],"enhance":[52],"MDD":[54,129],"ability":[55],"second":[59],"language":[60],"(L2)":[61],"English.":[62],"Specifically,":[63],"proposed":[65],"model":[67,122],"composed":[69],"an":[71,74,78],"audio":[72,85,89],"encoder,":[73],"LLM":[75,103],"decoder,":[76],"adapter.":[79],"Taking":[80],"speech":[81],"representations":[82],"from":[83],"encoder":[86],"as":[87,99],"reference":[92],"sentence":[93],"with":[94],"canonical":[95],"text":[100],"prompt,":[101],"decoder":[104],"adapted":[106],"predict":[108],"actual":[110],"pronunciation":[111,138],"given":[114],"L2":[115],"speech.":[116],"Experiments":[117],"show":[118],"that":[119],"our":[120],"achieves":[123],"new":[124],"state-of-the-art":[125],"(SOTA)":[126],"performance":[127],"on":[130],"CU-CHLOE":[131],"corpus,":[132],"confirming":[133],"effectiveness":[135],"integration.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}