{"id":"https://openalex.org/W4415433041","doi":"https://doi.org/10.21437/interspeech.2025-1868","title":"MVP: Multi-source Voice Pathology detection","display_name":"MVP: Multi-source Voice Pathology detection","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433041","doi":"https://doi.org/10.21437/interspeech.2025-1868"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1868","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1868","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":["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/A5083365850","display_name":"Alkis Koudounas","orcid":"https://orcid.org/0000-0003-4386-0409"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alkis Koudounas","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078641012","display_name":"Moreno La Quatra","orcid":"https://orcid.org/0000-0001-8838-064X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moreno La Quatra","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088953993","display_name":"Gabriele Ciravegna","orcid":"https://orcid.org/0000-0002-6799-1043"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gabriele Ciravegna","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082375786","display_name":"Marco Fantini","orcid":"https://orcid.org/0000-0002-4007-6259"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marco Fantini","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086363838","display_name":"Erika Crosetti","orcid":"https://orcid.org/0000-0003-4340-9677"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erika Crosetti","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020735860","display_name":"Giovanni Succo","orcid":"https://orcid.org/0000-0003-0375-6623"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giovanni Succo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053742461","display_name":"Tania Cerquitelli","orcid":"https://orcid.org/0000-0002-9039-6226"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tania Cerquitelli","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001695309","display_name":"Elena Baralis","orcid":"https://orcid.org/0000-0001-9231-467X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elena Baralis","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5083365850"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16658323,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3548","last_page":"3552"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8727999925613403,"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":0.8727999925613403,"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":0.8313000202178955,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.49129998683929443},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45190000534057617},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.42640000581741333},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.42260000109672546},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4198000133037567},{"id":"https://openalex.org/keywords/human-voice","display_name":"Human voice","score":0.35199999809265137},{"id":"https://openalex.org/keywords/voice-disorder","display_name":"Voice Disorder","score":0.34779998660087585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6779999732971191},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6079999804496765},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.49129998683929443},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4381999969482422},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4198000133037567},{"id":"https://openalex.org/C20766975","wikidata":"https://www.wikidata.org/wiki/Q7390","display_name":"Human voice","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C2908717642","wikidata":"https://www.wikidata.org/wiki/Q4593337","display_name":"Voice Disorder","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32910001277923584},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-1868","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1868","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:iris.unipa.it:10447/694127","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/694127","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","issn_l":null,"issn":null,"is_oa":false,"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":"info:eu-repo/semantics/bookPart"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Voice":[0,34],"disorders":[1],"significantly":[2],"impact":[3],"patient":[4],"quality":[5],"of":[6,19,91],"life,":[7],"yet":[8],"non-invasive":[9],"automated":[10],"diagnosis":[11],"remains":[12],"under-explored":[13],"due":[14],"to":[15,54,99],"both":[16,92],"the":[17,24,73,88],"scarcity":[18],"pathological":[20],"voice":[21,47],"data,":[22],"and":[23,58,67,76],"variability":[25],"in":[26],"recording":[27,93],"sources.":[28],"This":[29],"work":[30],"introduces":[31],"MVP":[32],"(Multi-source":[33],"Pathology":[35],"detection),":[36],"a":[37],"novel":[38],"approach":[39,96],"that":[40,80],"leverages":[41],"transformers":[42,85],"operating":[43],"directly":[44],"on":[45],"raw":[46],"signals.":[48],"We":[49],"explore":[50],"three":[51],"fusion":[52,83],"strategies":[53],"combine":[55],"sentence":[56],"reading":[57],"sustained":[59],"vowel":[60],"recordings:":[61],"waveform":[62],"concatenation,":[63],"intermediate":[64,81],"feature":[65,82],"fusion,":[66],"decision-level":[68],"combination.":[69],"Empirical":[70],"validation":[71],"across":[72],"German,":[74],"Portuguese,":[75],"Italian":[77],"languages":[78],"shows":[79],"using":[84],"best":[86],"captures":[87],"complementary":[89],"characteristics":[90],"types.":[94],"Our":[95],"achieves":[97],"up":[98],"+13%":[100],"AUC":[101],"improvement":[102],"over":[103],"single-source":[104],"methods.":[105]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}
