{"id":"https://openalex.org/W4415035350","doi":"https://doi.org/10.21437/interspeech.2025-41","title":"VocalAgent: Large Language Models for Vocal Health Diagnostics with Safety-Aware Evaluation","display_name":"VocalAgent: Large Language Models for Vocal Health Diagnostics with Safety-Aware Evaluation","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415035350","doi":"https://doi.org/10.21437/interspeech.2025-41"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-41","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-41","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.13577","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108104844","display_name":"Yubin Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yubin Kim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101747208","display_name":"Taehan Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taehan Kim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119938066","display_name":"Wonjune Kang","orcid":"https://orcid.org/0000-0002-5363-706X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wonjune Kang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112952445","display_name":"Eugene Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eugene Park","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023679281","display_name":"Joonsik Yoon","orcid":"https://orcid.org/0000-0002-9675-4944"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joonsik Yoon","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119938067","display_name":"Dongjae Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongjae Lee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352299","display_name":"Xin Liu","orcid":"https://orcid.org/0000-0003-0838-1904"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100681741","display_name":"Daniel McDuff","orcid":"https://orcid.org/0000-0001-7313-0082"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel McDuff","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026474928","display_name":"Hyeonhoon Lee","orcid":"https://orcid.org/0000-0002-9426-823X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyeonhoon Lee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108541589","display_name":"Cynthia Breazeal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cynthia Breazeal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102016303","display_name":"Hae Won Park","orcid":"https://orcid.org/0000-0001-9638-1722"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hae Won Park","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5108104844"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37122311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4618","last_page":"4622"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9987999796867371,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9904999732971191,"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/T11309","display_name":"Music and Audio Processing","score":0.9779999852180481,"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/leverage","display_name":"Leverage (statistics)","score":0.6678000092506409},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4223000109195709},{"id":"https://openalex.org/keywords/voice-disorder","display_name":"Voice Disorder","score":0.38850000500679016},{"id":"https://openalex.org/keywords/hedge","display_name":"Hedge","score":0.3605000078678131},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.36010000109672546},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.3409999907016754}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6678000092506409},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5149999856948853},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C2908717642","wikidata":"https://www.wikidata.org/wiki/Q4593337","display_name":"Voice Disorder","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3702000081539154},{"id":"https://openalex.org/C70771513","wikidata":"https://www.wikidata.org/wiki/Q235779","display_name":"Hedge","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3249000012874603},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3183000087738037},{"id":"https://openalex.org/C2779328685","wikidata":"https://www.wikidata.org/wiki/Q1475557","display_name":"Patient safety","level":3,"score":0.31439998745918274},{"id":"https://openalex.org/C75630572","wikidata":"https://www.wikidata.org/wiki/Q538904","display_name":"Applied psychology","level":1,"score":0.3057999908924103},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.30250000953674316},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26510000228881836},{"id":"https://openalex.org/C2250968","wikidata":"https://www.wikidata.org/wiki/Q1512929","display_name":"Health equity","level":3,"score":0.262800008058548},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-41","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-41","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.13577","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.13577","pdf_url":"https://arxiv.org/pdf/2505.13577","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:2505.13577","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.13577","pdf_url":"https://arxiv.org/pdf/2505.13577","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vocal":[0],"health":[1,48,106],"plays":[2],"a":[3,64,69,99],"crucial":[4],"role":[5],"in":[6],"peoples'":[7],"lives,":[8],"significantly":[9],"impacting":[10],"their":[11],"communicative":[12],"abilities":[13],"and":[14,30,62,79,114],"interactions.":[15],"However,":[16],"despite":[17],"the":[18,110],"global":[19],"prevalence":[20],"of":[21,105,112],"voice":[22,88],"disorders,":[23],"many":[24],"lack":[25],"access":[26],"to":[27,42,72,92],"convenient":[28],"diagnosis":[29],"treatment.":[31],"This":[32],"paper":[33],"introduces":[34],"VocalAgent,":[35],"an":[36],"audio":[37],"large":[38],"language":[39],"model":[40],"(LLM)":[41],"address":[43],"these":[44],"challenges":[45],"through":[46],"vocal":[47],"diagnosis.":[49],"We":[50],"leverage":[51],"Qwen-Audio-Chat":[52],"fine-tuned":[53],"on":[54,87],"three":[55],"datasets":[56],"collected":[57],"in-situ":[58],"from":[59],"hospital":[60],"patients,":[61],"present":[63],"multifaceted":[65],"evaluation":[66],"framework":[67],"encompassing":[68],"safety":[70],"assessment":[71],"mitigate":[73],"diagnostic":[74],"biases,":[75],"cross-lingual":[76],"performance":[77],"analysis,":[78],"modality":[80],"ablation":[81],"studies.":[82],"VocalAgent":[83],"demonstrates":[84],"superior":[85],"accuracy":[86],"disorder":[89],"classification":[90],"compared":[91],"state-of-the-art":[93],"baselines.":[94],"Its":[95],"LLM-based":[96],"method":[97],"offers":[98],"scalable":[100],"solution":[101],"for":[102],"broader":[103],"adoption":[104],"diagnostics,":[107],"while":[108],"underscoring":[109],"importance":[111],"ethical":[113],"technical":[115],"validation.":[116]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}