{"id":"https://openalex.org/W4361986430","doi":"https://doi.org/10.1109/taslp.2023.3261753","title":"Robust Vocal Quality Feature Embeddings for Dysphonic Voice Detection","display_name":"Robust Vocal Quality Feature Embeddings for Dysphonic Voice Detection","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4361986430","doi":"https://doi.org/10.1109/taslp.2023.3261753","pmid":"https://pubmed.ncbi.nlm.nih.gov/37899766"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3261753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3261753","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10602198/pdf/nihms-1890722.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100326952","display_name":"Jianwei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jianwei Zhang","raw_affiliation_strings":["School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA"],"raw_orcid":"https://orcid.org/0000-0001-6419-2038","affiliations":[{"raw_affiliation_string":"School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056934840","display_name":"Julie Liss","orcid":"https://orcid.org/0000-0001-8782-2901"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julie Liss","raw_affiliation_strings":["College of Health Solutions, Arizona State University, Tempe, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Health Solutions, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043608888","display_name":"Suren Jayasuriya","orcid":"https://orcid.org/0000-0001-7143-4429"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suren Jayasuriya","raw_affiliation_strings":["School of Arts, Media and Engineering and the School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA"],"raw_orcid":"https://orcid.org/0000-0001-7143-4429","affiliations":[{"raw_affiliation_string":"School of Arts, Media and Engineering and the School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021646973","display_name":"Visar Berisha","orcid":"https://orcid.org/0000-0001-8804-8874"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Visar Berisha","raw_affiliation_strings":["College of Health Solutions and School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Health Solutions and School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100326952"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":1.3638,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80292466,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"1348","last_page":"1359"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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":0.9997000098228455,"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/computer-science","display_name":"Computer science","score":0.7963451147079468},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7703215479850769},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.661598801612854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5448011755943298},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5136103630065918},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46773964166641235},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.4383634626865387},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42674383521080017},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3495748043060303}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7963451147079468},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7703215479850769},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.661598801612854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5448011755943298},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5136103630065918},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46773964166641235},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.4383634626865387},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42674383521080017},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3495748043060303},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2023.3261753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3261753","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmid:37899766","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37899766","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM transactions on audio, speech, and language processing","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10602198","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10602198","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10602198/pdf/nihms-1890722.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:10602198","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10602198","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10602198/pdf/nihms-1890722.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2101059215","display_name":null,"funder_award_id":"R01DC006859","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"},{"id":"https://openalex.org/G7061349327","display_name":null,"funder_award_id":"R01DC006859","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4361986430.pdf"},"referenced_works_count":72,"referenced_works":["https://openalex.org/W110017167","https://openalex.org/W131583169","https://openalex.org/W639540966","https://openalex.org/W1446439765","https://openalex.org/W2004528618","https://openalex.org/W2024375869","https://openalex.org/W2033251050","https://openalex.org/W2034790228","https://openalex.org/W2046056978","https://openalex.org/W2078169166","https://openalex.org/W2085662862","https://openalex.org/W2085806873","https://openalex.org/W2114925438","https://openalex.org/W2132025473","https://openalex.org/W2136682440","https://openalex.org/W2162833336","https://openalex.org/W2179209501","https://openalex.org/W2191779130","https://openalex.org/W2290080275","https://openalex.org/W2506429203","https://openalex.org/W2552697641","https://openalex.org/W2555915854","https://openalex.org/W2581209700","https://openalex.org/W2612112834","https://openalex.org/W2612434969","https://openalex.org/W2738314890","https://openalex.org/W2789416342","https://openalex.org/W2790046776","https://openalex.org/W2803843034","https://openalex.org/W2807317037","https://openalex.org/W2883781843","https://openalex.org/W2889326414","https://openalex.org/W2896457183","https://openalex.org/W2898866157","https://openalex.org/W2959813266","https://openalex.org/W2962788625","https://openalex.org/W2963350250","https://openalex.org/W2964692166","https://openalex.org/W2973154337","https://openalex.org/W2990089290","https://openalex.org/W2997591727","https://openalex.org/W3027101363","https://openalex.org/W3031948080","https://openalex.org/W3035524453","https://openalex.org/W3036601975","https://openalex.org/W3045814128","https://openalex.org/W3045825772","https://openalex.org/W3106436761","https://openalex.org/W3110175868","https://openalex.org/W3125384922","https://openalex.org/W3163573274","https://openalex.org/W3168186795","https://openalex.org/W3196473068","https://openalex.org/W3197558453","https://openalex.org/W3204408661","https://openalex.org/W3208504364","https://openalex.org/W3216401400","https://openalex.org/W4210487887","https://openalex.org/W4232282348","https://openalex.org/W4242280121","https://openalex.org/W4311000453","https://openalex.org/W6604471452","https://openalex.org/W6732679647","https://openalex.org/W6737575990","https://openalex.org/W6750489868","https://openalex.org/W6755207826","https://openalex.org/W6766978945","https://openalex.org/W6777179611","https://openalex.org/W6778883912","https://openalex.org/W6780218876","https://openalex.org/W6783182287","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2030799363","https://openalex.org/W2950183183","https://openalex.org/W2341338763","https://openalex.org/W2288425735","https://openalex.org/W2349923317","https://openalex.org/W2894081631","https://openalex.org/W2986063033","https://openalex.org/W2040439981","https://openalex.org/W2472888994","https://openalex.org/W3000197790"],"abstract_inverted_index":{"Approximately":[0],"1.2%":[1],"of":[2,96,142],"the":[3,36,94,151,156],"world's":[4],"population":[5],"has":[6,17],"impaired":[7],"voice":[8,15,29,90,121],"production.":[9],"As":[10],"a":[11,49,73],"result,":[12],"automatic":[13],"dysphonic":[14],"detection":[16],"attracted":[18],"considerable":[19],"academic":[20],"and":[21,62,110,123,139,145,148],"clinical":[22],"interest.":[23],"However,":[24],"existing":[25],"methods":[26,85,136],"for":[27,53],"automated":[28],"assessment":[30],"often":[31],"fail":[32],"to":[33,40,59,76,92,120],"generalize":[34],"outside":[35],"training":[37],"conditions":[38],"or":[39],"other":[41],"related":[42],"applications.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47],"propose":[48],"deep":[50,79],"learning":[51,80],"framework":[52],"generating":[54],"acoustic":[55],"feature":[56],"embeddings":[57,118],"sensitive":[58,119],"vocal":[60],"quality":[61,122],"robust":[63,124],"across":[64,125],"different":[65,126],"corpora.":[66,127],"A":[67],"contrastive":[68],"loss":[69,75],"is":[70],"combined":[71],"with":[72],"classification":[74,112],"train":[77],"our":[78,97,103,131],"model":[81,153],"jointly.":[82],"Data":[83],"warping":[84],"are":[86],"used":[87],"on":[88,137],"input":[89],"samples":[91],"improve":[93],"robustness":[95],"method.":[98],"Empirical":[99],"results":[100,132],"demonstrate":[101,149],"that":[102,150],"method":[104],"not":[105],"only":[106],"achieves":[107],"high":[108],"in-corpus":[109,144],"cross-corpus":[111,146],"accuracy":[113],"but":[114],"also":[115,129],"generates":[116],"good":[117],"We":[128],"compare":[130],"against":[133],"three":[134,140],"baseline":[135,157],"clean":[138],"variations":[141],"deteriorated":[143],"datasets":[147],"proposed":[152],"consistently":[154],"outperforms":[155],"methods.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}