{"id":"https://openalex.org/W7220748460","doi":null,"title":"Augmenting Large Audio Language Models with Low-Level Acoustic Features for Dysarthric Speech Detection","display_name":"Augmenting Large Audio Language Models with Low-Level Acoustic Features for Dysarthric Speech Detection","publication_year":2026,"publication_date":"2026-10-02","ids":{"openalex":"https://openalex.org/W7220748460"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.03352","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.03352","pdf_url":"https://arxiv.org/pdf/2610.03352","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","is_traditional":true,"indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.03352","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101998063","display_name":"Mahdi Amiri","orcid":"https://orcid.org/0000-0002-8779-9606","observed_orcids":["https://orcid.org/0000-0002-8779-9606"]},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Amiri, Mahdi","raw_affiliation_strings":["Idiap Research Institute , Switzerland","\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL) , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute , Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL) , Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042428131","display_name":"Hatef Otroshi Shahreza","orcid":"https://orcid.org/0000-0002-8199-0098","observed_orcids":["https://orcid.org/0000-0002-8199-0098"]},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Shahreza, Hatef Otroshi","raw_affiliation_strings":["Idiap Research Institute , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute , Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000947076","display_name":"Pascal Frossard","orcid":"https://orcid.org/0000-0002-4010-714X","observed_orcids":["https://orcid.org/0000-0002-4010-714X"]},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Frossard, Pascal","raw_affiliation_strings":["\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL) , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL) , Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061058558","display_name":"Ina Kodrasi","orcid":"https://orcid.org/0000-0002-1747-1322","observed_orcids":["https://orcid.org/0000-0002-1747-1322"]},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Kodrasi, Ina","raw_affiliation_strings":["Idiap Research Institute , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute , Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.5659000277519226,"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":0.5659000277519226,"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/T10863","display_name":"Voice and Speech Disorders","score":0.4284999966621399,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.002199999988079071,"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/large-audio-language-models","display_name":"large audio language models","score":0.9890000224113464},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.8169999718666077},{"id":"https://openalex.org/keywords/speaker-demographics","display_name":"speaker demographics","score":0.8970000147819519},{"id":"https://openalex.org/keywords/speech-disorders","display_name":"speech disorders","score":0.34700000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7390000224113464},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7195000052452087},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46560001373291016},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4390000104904175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4221999943256378},{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.4115999937057495},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3619000017642975},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32580000162124634},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.3149000108242035},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.26840001344680786},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26759999990463257}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2610.03352","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.03352","pdf_url":"https://arxiv.org/pdf/2610.03352","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.03352","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.03352","pdf_url":"https://arxiv.org/pdf/2610.03352","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":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.46810001134872437}],"study_designs":[],"awards":[{"id":"https://openalex.org/G6415372598","display_name":"Characterisation of motor speech disorders and processes (ChaSpeePro)","funder_award_id":"202228","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220748460.pdf","grobid_xml":"https://content.openalex.org/works/W7220748460.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W3213029956","https://openalex.org/W4387225871","https://openalex.org/W4400717319","https://openalex.org/W4404330874","https://openalex.org/W4415085804"],"related_works":["https://openalex.org/W7131434109","https://openalex.org/W4407579958","https://openalex.org/W4327935670","https://openalex.org/W4391825007","https://openalex.org/W4410342580","https://openalex.org/W2961221611","https://openalex.org/W4415432901","https://openalex.org/W7160322785","https://openalex.org/W7063767204","https://openalex.org/W4408355119"],"abstract_inverted_index":{"Automatic":[0],"dysarthric":[1,56,72,136],"speech":[2,19,57,73,76,137],"detection":[3,58,74],"approaches":[4,25],"can":[5],"support":[6],"traditional":[7],"clinical":[8],"diagnosis,":[9],"which":[10],"relies":[11],"on":[12,28,75],"costly":[13],"and":[14,20,86,110],"time-consuming":[15],"evaluation":[16],"by":[17],"a":[18,42,66],"language":[21],"pathologist.":[22],"Existing":[23],"automatic":[24],"predominantly":[26],"rely":[27],"deep":[29],"learning":[30],"(DL).":[31],"More":[32],"recently,":[33],"Large":[34],"Audio":[35],"Language":[36],"Models":[37],"(LALMs)":[38],"have":[39],"emerged":[40],"as":[41],"promising":[43],"alternative":[44],"given":[45],"their":[46,53],"strong":[47],"performance":[48],"across":[49],"various":[50],"tasks,":[51],"but":[52],"application":[54],"to":[55,135],"has":[59],"not":[60],"yet":[61],"been":[62],"established.":[63],"We":[64],"propose":[65],"framework":[67,93],"that":[68,106],"fine-tunes":[69],"LALMs":[70,119,134],"for":[71,132],"recordings":[77],"combined":[78],"with":[79,97],"textual":[80],"information":[81],"comprising":[82],"low-level":[83],"acoustic":[84,108],"features":[85,109],"speaker":[87,111],"demographics.":[88],"Across":[89],"two":[90],"LALMs,":[91],"our":[92],"outperforms":[94],"DL-based":[95],"baselines,":[96],"Qwen2-Audio-Instruct":[98],"achieving":[99],"state-of-the-art":[100],"performance.":[101,125],"An":[102],"ablation":[103],"study":[104],"shows":[105],"incorporating":[107],"demographics":[112],"during":[113],"fine-tuning":[114],"improves":[115],"LALM":[116],"performance,":[117],"while":[118],"alone":[120],"exhibit":[121],"only":[122],"chance-level":[123],"zero-shot":[124],"These":[126],"findings":[127],"establish":[128],"an":[129],"effective":[130],"approach":[131],"adapting":[133],"detection.":[138]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-07T00:00:00"}