{"id":"https://openalex.org/W4416799914","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248999","title":"Parameter-Efficient Fine-Tuning of Foundation Models for CLP Speech Classification","display_name":"Parameter-Efficient Fine-Tuning of Foundation Models for CLP Speech Classification","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799914","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248999"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11248999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5103222616","display_name":"Susmita Bhattacharjee","orcid":"https://orcid.org/0009-0009-0169-3420"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Susmita Bhattacharjee","raw_affiliation_strings":["Indian Institute of Technology Guwahati,Guwahati"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Guwahati,Guwahati","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013209021","display_name":"Jagabandhu Mishra","orcid":"https://orcid.org/0000-0003-1878-6286"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"id":"https://openalex.org/I4210106278","display_name":"Joensuu Science Park","ror":"https://ror.org/01j45tp19","country_code":"FI","type":"company","lineage":["https://openalex.org/I4210106278"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jagabandhu Mishra","raw_affiliation_strings":["University of Eastern Finland,Joensuu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Eastern Finland,Joensuu","institution_ids":["https://openalex.org/I4210106278","https://openalex.org/I175532246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032240951","display_name":"Hanumant Singh Shekhawat","orcid":null},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"H.S. Shekhawat","raw_affiliation_strings":["Indian Institute of Technology Guwahati,Guwahati"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Guwahati,Guwahati","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052129812","display_name":"S. R. Mahadeva Prasanna","orcid":"https://orcid.org/0000-0002-8135-7938"},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. R. Mahadeva Prasanna","raw_affiliation_strings":["Indian Institute of Information Technology Dharwad,Dharwad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology Dharwad,Dharwad","institution_ids":["https://openalex.org/I4210152718"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35054376,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1080","last_page":"1085"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11374","display_name":"Cleft Lip and Palate Research","score":0.8464000225067139,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11374","display_name":"Cleft Lip and Palate Research","score":0.8464000225067139,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.0982000008225441,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.017999999225139618,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/nasalization","display_name":"Nasalization","score":0.5162000060081482},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.43470001220703125},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4223000109195709},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4129999876022339},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.39879998564720154},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.3978999853134155},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3952000141143799},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.375900000333786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7009999752044678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5949000120162964},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5270000100135803},{"id":"https://openalex.org/C516976414","wikidata":"https://www.wikidata.org/wiki/Q1606582","display_name":"Nasalization","level":3,"score":0.5162000060081482},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.43470001220703125},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41200000047683716},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.375900000333786},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3635999858379364},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35109999775886536},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.31349998712539673},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.28459998965263367},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C67795661","wikidata":"https://www.wikidata.org/wiki/Q17018993","display_name":"Shearlet","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C196070930","wikidata":"https://www.wikidata.org/wiki/Q598190","display_name":"Correlogram","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11248999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/W1971169033","https://openalex.org/W2060052977","https://openalex.org/W2087494890","https://openalex.org/W2098477407","https://openalex.org/W2143410152","https://openalex.org/W2144005487","https://openalex.org/W2171277043","https://openalex.org/W2239141610","https://openalex.org/W2747395251","https://openalex.org/W2888807234","https://openalex.org/W2995235118","https://openalex.org/W3015897612","https://openalex.org/W3129068537","https://openalex.org/W3209984917","https://openalex.org/W4210252722","https://openalex.org/W4289829928","https://openalex.org/W4378349013","https://openalex.org/W4385823068","https://openalex.org/W4401413559","https://openalex.org/W4408793185","https://openalex.org/W4409806039","https://openalex.org/W4415432873"],"related_works":[],"abstract_inverted_index":{"We":[0,83,94],"propose":[1],"the":[2,29,33,71,108,130,149,167,176,186],"use":[3],"of":[4,8,158,181],"parameter-efficient":[5],"finetuning":[6],"(PEFT)":[7],"foundation":[9,56,169],"models":[10,57,103],"for":[11,60,152],"cleft":[12],"lip":[13],"and":[14,18,35,48,52,91,105,107,117,125,140,160,171,179,183],"palate":[15],"(CLP)":[16],"detection":[17],"severity":[19,26,77,153],"classification.":[20],"In":[21],"CLP,":[22],"nasalization":[23],"increases":[24],"with":[25,114,121],"due":[27],"to":[28,42,73],"abnormal":[30],"passage":[31],"between":[32],"oral":[34,40],"nasal":[36],"tracts;":[37],"this":[38],"causes":[39],"stops":[41,47],"be":[43],"replaced":[44],"by":[45],"glottal":[46],"alters":[49],"formant":[50],"trajectories":[51],"vowel":[53],"space.":[54],"Since":[55],"are":[58],"trained":[59],"grapheme":[61],"prediction":[62],"or":[63],"long-term":[64],"quantized":[65],"representation":[66],"prediction,":[67],"they":[68],"might":[69],"have":[70],"potential":[72],"better":[74],"discriminate":[75],"CLP":[76],"when":[78],"finetuned":[79],"on":[80,86,175,185],"domain-specific":[81],"data.":[82],"conduct":[84],"experiments":[85],"two":[87],"datasets:":[88],"English":[89],"(NMCPC)":[90],"Kannada":[92],"(AIISH).":[93],"perform":[95],"a":[96],"comparative":[97],"analysis":[98],"using":[99,134],"embeddings":[100],"from":[101],"self-supervised":[102],"Wav2Vec2":[104],"WavLM,":[106],"weakly":[109],"supervised":[110],"Whisper,":[111],"each":[112],"paired":[113],"SVM":[115],"classifiers,":[116],"compare":[118],"their":[119],"results":[120,146],"traditional":[122],"handcrafted":[123,172],"features\u2014eGeMAPS":[124],"ComParE.":[126],"Finally,":[127],"we":[128],"fine-tune":[129],"best-performing":[131],"Whisper":[132],"model":[133,170],"PEFT":[135],"techniques:":[136],"Low-Rank":[137,142],"Adapter":[138,143],"(LoRA)":[139],"Decomposed":[141],"(DoRA).":[144],"Our":[145],"demonstrate":[147],"that":[148],"proposed":[150],"approach":[151],"classification":[154],"achieves":[155],"relative":[156],"improvements":[157,180],"26.4%":[159],"63.4%":[161],"in":[162],"macro-average":[163],"F1":[164],"score":[165],"over":[166],"best":[168],"feature":[173],"baselines":[174],"NMCPC":[177],"dataset,":[178,188],"6.1%":[182],"52.9%":[184],"AIISH":[187],"respectively.":[189]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}