{"id":"https://openalex.org/W4417409463","doi":"https://doi.org/10.48550/arxiv.2509.02915","title":"English Pronunciation Evaluation without Complex Joint Training: LoRA Fine-tuned Speech Multimodal LLM","display_name":"English Pronunciation Evaluation without Complex Joint Training: LoRA Fine-tuned Speech Multimodal LLM","publication_year":2025,"publication_date":"2025-09-03","ids":{"openalex":"https://openalex.org/W4417409463","doi":"https://doi.org/10.48550/arxiv.2509.02915"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2509.02915","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.02915","pdf_url":"https://arxiv.org/pdf/2509.02915","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.02915","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082791363","display_name":"Taekyung Ahn","orcid":"https://orcid.org/0009-0003-9394-1650","observed_orcids":["https://orcid.org/0009-0003-9394-1650"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahn, Taekyung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5058543204","display_name":"Hosung Nam","orcid":"https://orcid.org/0000-0002-1523-346X","observed_orcids":["https://orcid.org/0000-0002-1523-346X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nam, Hosung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9717000126838684,"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":0.9717000126838684,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.011800000444054604,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.003700000001117587,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/automatic-pronunciation-assessment","display_name":"automatic pronunciation assessment","score":0.9200000166893005},{"id":"https://openalex.org/keywords/mispronunciation-detection","display_name":"mispronunciation detection","score":0.8690000176429749},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.828000009059906},{"id":"https://openalex.org/keywords/low-rank-adaptation","display_name":"low-rank adaptation","score":0.8769999742507935},{"id":"https://openalex.org/keywords/english-pronunciation","display_name":"English pronunciation","score":0.5659999847412109},{"id":"https://openalex.org/keywords/computer-assisted-pronunciation-training","display_name":"computer-assisted pronunciation training","score":0.9449999928474426},{"id":"https://openalex.org/keywords/second-language-learners","display_name":"second language learners","score":0.6859999895095825},{"id":"https://openalex.org/keywords/audiovisual-speech","display_name":"audiovisual speech","score":0.421999990940094}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.9485999941825867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8051000237464905},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7186999917030334},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6524999737739563},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6315000057220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4909000098705292},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.46389999985694885},{"id":"https://openalex.org/C55078378","wikidata":"https://www.wikidata.org/wiki/Q1136628","display_name":"Pearson product-moment correlation coefficient","level":2,"score":0.4546000063419342},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4106000065803528},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C2780092901","wikidata":"https://www.wikidata.org/wiki/Q3433612","display_name":"Correlation coefficient","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C126669455","wikidata":"https://www.wikidata.org/wiki/Q1630941","display_name":"Teleconference","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26660001277923584},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2509.02915","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.02915","pdf_url":"https://arxiv.org/pdf/2509.02915","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.02915","doi":"https://doi.org/10.48550/arxiv.2509.02915","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.02915","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.02915","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.02915","pdf_url":"https://arxiv.org/pdf/2509.02915","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4414700412","https://openalex.org/W4385823114","https://openalex.org/W4417072987","https://openalex.org/W7057592585","https://openalex.org/W7119725237","https://openalex.org/W4408353580","https://openalex.org/W4417284056","https://openalex.org/W7118412729","https://openalex.org/W7140112366","https://openalex.org/W4406858977"],"abstract_inverted_index":{"This":[0,113,150],"study":[1],"demonstrates":[2],"that":[3,116],"a":[4,66,134],"Multimodal":[5],"Large":[6],"Language":[7],"Model":[8],"(MLLM)":[9],"adapted":[10],"via":[11],"Low-Rank":[12],"Adaptation":[13],"(LoRA)":[14],"can":[15,122],"perform":[16],"both":[17],"Automatic":[18],"Pronunciation":[19,164],"Assessment":[20],"(APA)":[21],"and":[22,25,84,148,161],"Mispronunciation":[23],"Detection":[24],"Diagnosis":[26],"(MDD)":[27],"simultaneously.":[28],"Leveraging":[29],"Microsoft's":[30],"Phi-4-multimodal-instruct,":[31],"our":[32],"fine-tuning":[33,93,109],"method":[34],"eliminates":[35],"the":[36,54,57,63,95,155],"need":[37],"for":[38,48,145,157,168],"complex":[39],"architectural":[40],"changes":[41],"or":[42],"separate":[43],"training":[44,137],"procedures":[45],"conventionally":[46],"required":[47],"these":[49],"distinct":[50],"tasks.":[51],"Fine-tuned":[52],"on":[53],"Speechocean762":[55],"dataset,":[56],"pronunciation":[58,119],"evaluation":[59],"scores":[60],"predicted":[61],"by":[62,108,125],"model":[64],"exhibited":[65],"strong":[67],"Pearson":[68],"Correlation":[69],"Coefficient":[70],"(PCC":[71],">":[72],"0.7)":[73],"with":[74],"human-assigned":[75],"scores,":[76],"while":[77],"achieving":[78],"low":[79],"Word":[80],"Error":[81,86],"Rate":[82,87],"(WER)":[83],"Phoneme":[85],"(PER)":[88],"(both":[89],"<":[90],"0.15).":[91],"Notably,":[92],"only":[94],"LoRA":[96],"layers":[97],"was":[98],"sufficient":[99],"to":[100,105,140],"achieve":[101],"performance":[102],"levels":[103],"comparable":[104],"those":[106],"achieved":[107],"all":[110],"audio":[111],"layers.":[112],"research":[114],"highlights":[115],"an":[117],"integrated":[118],"assessment":[120],"system":[121],"be":[123],"established":[124],"adapting":[126],"large":[127],"multimodal":[128],"models":[129,143],"without":[130],"full":[131],"fine-tuning,":[132],"utilizing":[133],"significantly":[135],"simpler":[136],"methodology":[138],"compared":[139],"previous":[141],"joint":[142],"designed":[144],"simultaneous":[146],"APA":[147],"MDD.":[149],"efficient":[151],"LoRA-based":[152],"approach":[153],"paves":[154],"way":[156],"more":[158],"accessible,":[159],"integrated,":[160],"effective":[162],"Computer-Assisted":[163],"Training":[165],"(CAPT)":[166],"technologies":[167],"English":[169],"L2":[170],"learners.":[171]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}