{"id":"https://openalex.org/W3015705854","doi":"https://doi.org/10.1109/icassp40776.2020.9053770","title":"Using X-Vectors to Automatically Detect Parkinson\u2019s Disease from Speech","display_name":"Using X-Vectors to Automatically Detect Parkinson\u2019s Disease from Speech","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015705854","doi":"https://doi.org/10.1109/icassp40776.2020.9053770","mag":"3015705854"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5069488212","display_name":"Laureano Moro-Vel\u00e1zquez","orcid":"https://orcid.org/0000-0002-3033-7005"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Laureano Moro-Velazquez","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057010207","display_name":"Jes\u00fas Villalba","orcid":"https://orcid.org/0000-0001-9459-8426"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jesus Villalba","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069488212"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":3.4781,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.93479892,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1155","last_page":"1159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9984999895095825,"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/T10860","display_name":"Speech and Audio Processing","score":0.9898999929428101,"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/speech-recognition","display_name":"Speech recognition","score":0.7418338060379028},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7252810597419739},{"id":"https://openalex.org/keywords/phonation","display_name":"Phonation","score":0.7235807180404663},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6803744435310364},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5675508975982666},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.5503062605857849},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5283592343330383},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4851852059364319},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4758013188838959},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46274617314338684},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42734023928642273},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4231213927268982},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4131212532520294},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.09089380502700806},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.08441871404647827}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7418338060379028},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7252810597419739},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.7235807180404663},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6803744435310364},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5675508975982666},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.5503062605857849},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5283592343330383},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4851852059364319},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4758013188838959},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46274617314338684},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42734023928642273},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4231213927268982},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4131212532520294},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.09089380502700806},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.08441871404647827},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W191801690","https://openalex.org/W1524333225","https://openalex.org/W1562359367","https://openalex.org/W1589137271","https://openalex.org/W2010817634","https://openalex.org/W2041823554","https://openalex.org/W2064996887","https://openalex.org/W2093977564","https://openalex.org/W2150769028","https://openalex.org/W2170088868","https://openalex.org/W2281923782","https://openalex.org/W2323830726","https://openalex.org/W2394484369","https://openalex.org/W2405176157","https://openalex.org/W2417001119","https://openalex.org/W2514356239","https://openalex.org/W2726515241","https://openalex.org/W2747514149","https://openalex.org/W2769607762","https://openalex.org/W2807627734","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2897435617","https://openalex.org/W2899053767","https://openalex.org/W2899467104","https://openalex.org/W2972403660","https://openalex.org/W2972481817","https://openalex.org/W2972961496","https://openalex.org/W2973031805","https://openalex.org/W2979593053","https://openalex.org/W3008391559","https://openalex.org/W4289465850","https://openalex.org/W6631362777","https://openalex.org/W6635152626","https://openalex.org/W6740167877","https://openalex.org/W6756022612","https://openalex.org/W6768553363"],"related_works":["https://openalex.org/W1987047733","https://openalex.org/W2989774764","https://openalex.org/W1914697324","https://openalex.org/W2167212246","https://openalex.org/W2027982229","https://openalex.org/W3013996185","https://openalex.org/W4253972549","https://openalex.org/W3022089375","https://openalex.org/W1995243272","https://openalex.org/W2406897232"],"abstract_inverted_index":{"The":[0,78],"promise":[1],"of":[2,12,38,74,116,136,142],"new":[3,18,61],"neuroprotective":[4],"treatments":[5],"to":[6,112,164],"stop":[7],"or":[8,20],"slow":[9],"the":[10,36,57,71,114,131],"advance":[11],"Parkinson's":[13],"Disease":[14],"(PD)":[15],"urges":[16],"for":[17,56],"biomarkers":[19],"detection":[21,48,73],"schemes":[22],"that":[23,30,150],"can":[24,45],"deliver":[25],"a":[26,60,68],"faster":[27],"diagnosis.":[28],"Given":[29],"speech":[31,43],"is":[32,81],"affected":[33],"by":[34],"PD,":[35],"combination":[37],"deep":[39,155],"neural":[40,156],"networks":[41,157],"and":[42,93,106,125,138,144],"processing":[44],"provide":[46],"automatic":[47,72],"schemes.":[49],"Accordingly,":[50],"in":[51,67,90,97,134,166,172],"this":[52,98],"study":[53],"we":[54],"analyze":[55],"first":[58],"time":[59],"state-of-the-art":[62],"speaker":[63,85,151],"recognition":[64,86],"technique,":[65,87],"x-Vectors,":[66],"different":[69],"scenario:":[70],"PD":[75,104],"from":[76],"speech.":[77],"proposed":[79],"approach":[80,129],"compared":[82],"with":[83,102,174],"another":[84],"i-Vectors,":[88],"employed":[89],"previous":[91],"works":[92],"used":[94,111],"as":[95],"baseline":[96],"study.":[99],"A":[100],"corpus":[101],"43":[103],"patients":[105],"46":[107],"control":[108],"speakers":[109],"was":[110],"evaluate":[113],"performance":[115],"these":[117],"two":[118,121],"techniques":[119],"at":[120],"sampling":[122],"frequencies:":[123],"8":[124],"16":[126],"kHz.The":[127],"x-Vector":[128],"provided":[130],"best":[132],"results":[133,148],"terms":[135],"accuracy":[137],"AUC":[139],"reaching":[140],"values":[141],"90%":[143],"0.94,":[145],"respectively.":[146],"Consequently,":[147],"suggest":[149],"embeddings":[152],"obtained":[153],"using":[154],"are":[158],"successful":[159],"extracting":[160],"acoustic":[161],"information":[162],"relative":[163],"patterns":[165],"articulation,":[167],"prosody":[168],"and/or":[169],"phonation":[170],"common":[171],"persons":[173],"PD.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":2}],"updated_date":"2026-01-20T17:24:06.736184","created_date":"2025-10-10T00:00:00"}