{"id":"https://openalex.org/W4402112142","doi":"https://doi.org/10.21437/interspeech.2024-522","title":"Exploiting Foundation Models and Speech Enhancement for Parkinson's Disease Detection from Speech in Real-World Operative Conditions","display_name":"Exploiting Foundation Models and Speech Enhancement for Parkinson's Disease Detection from Speech in Real-World Operative Conditions","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112142","doi":"https://doi.org/10.21437/interspeech.2024-522"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-522","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","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/A5078641012","display_name":"Moreno La Quatra","orcid":"https://orcid.org/0000-0001-8838-064X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Moreno La Quatra","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114218709","display_name":"Maria Francesca Turco","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maria Francesca Turco","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055323428","display_name":"Torbj\u00f8rn Svendsen","orcid":"https://orcid.org/0000-0003-0578-7941"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Torbj\u00f8rn Svendsen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029874932","display_name":"Giampiero Salvi","orcid":"https://orcid.org/0000-0002-3323-5311"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giampiero Salvi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014414626","display_name":"Juan Rafael Orozco\u2010Arroyave","orcid":"https://orcid.org/0000-0002-8507-0782"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juan Rafael Orozco-Arroyave","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","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":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5078641012"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.2959,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.97876359,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1405","last_page":"1409"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9959999918937683,"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":0.9959999918937683,"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":0.9225999712944031,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6057806015014648},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.5957932472229004},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5856937170028687},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5723859667778015},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4315890967845917},{"id":"https://openalex.org/keywords/parkinsons-disease","display_name":"Parkinson's disease","score":0.4153054356575012},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3173002600669861},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2975606620311737},{"id":"https://openalex.org/keywords/disease","display_name":"Disease","score":0.277929425239563},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.15423253178596497},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.06537795066833496},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.0643979012966156}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6057806015014648},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5957932472229004},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5856937170028687},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5723859667778015},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4315890967845917},{"id":"https://openalex.org/C2779734285","wikidata":"https://www.wikidata.org/wiki/Q11085","display_name":"Parkinson's disease","level":3,"score":0.4153054356575012},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3173002600669861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2975606620311737},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.277929425239563},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.15423253178596497},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.06537795066833496},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0643979012966156},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2024-522","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unipa.it:10447/670043","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/670043","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":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2955597484","https://openalex.org/W2373767407","https://openalex.org/W2653598178","https://openalex.org/W3110551121","https://openalex.org/W2747006289","https://openalex.org/W3160071434","https://openalex.org/W2851491717"],"abstract_inverted_index":{"This":[0],"work":[1],"is":[2,106],"concerned":[3],"with":[4],"devising":[5],"a":[6,76,101],"robust":[7],"Parkinson\u2019s":[8],"(PD)":[9],"disease":[10],"detector":[11],"from":[12,82],"speech":[13,24],"in":[14,70,79,104],"real-world":[15,71,85],"operating":[16],"conditions":[17,93],"using":[18],"(i)":[19],"foundational":[20],"models,":[21],"and":[22,74,91,100,126],"(ii)":[23],"enhancement":[25],"(SE)":[26],"methods.":[27],"To":[28],"this":[29],"end,":[30],"we":[31,54,88],"first":[32],"fine-tune":[33],"several":[34],"foundational-based":[35,111,118],"models":[36,62,119],"on":[37,63,98,121,132],"the":[38,56,60,64,110,115,133],"standard":[39],"PC-GITA":[40],"(s-PCGITA)":[41],"clean":[42],"data.":[43],"Our":[44],"results":[45],"demonstrate":[46],"superior":[47],"performance":[48,80,105,131],"to":[49,84],"previously":[50],"proposed":[51],"models.":[52,112],"Second,":[53],"assess":[55],"generalization":[57],"capability":[58],"of":[59],"PD":[61],"extended":[65],"PCGITA":[66],"(e-PC-GITA)":[67],"recordings,":[68],"collected":[69],"operative":[72],"conditions,":[73],"observe":[75],"severe":[77],"drop":[78],"moving":[81],"ideal":[83],"conditions.":[86],"Third,":[87],"align":[89],"training":[90],"testing":[92],"applaying":[94],"off-the-shelf":[95],"SE":[96],"techniques":[97],"e-PC-GITA,":[99],"significant":[102],"boost":[103],"observed":[107],"only":[108],"for":[109],"Finally,":[113],"combining":[114],"two":[116],"best":[117],"trained":[120],"s-PCGITA,":[122],"namely":[123],"WavLM":[124],"Base":[125],"Hubert":[127],"Base,":[128],"yielded":[129],"top":[130],"enhanced":[134],"e-PC-GITA":[135]},"counts_by_year":[{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
