{"id":"https://openalex.org/W2770890514","doi":"https://doi.org/10.1109/taslp.2017.2759002","title":"Modal and Nonmodal Voice Quality Classification Using Acoustic and Electroglottographic Features","display_name":"Modal and Nonmodal Voice Quality Classification Using Acoustic and Electroglottographic Features","publication_year":2017,"publication_date":"2017-11-27","ids":{"openalex":"https://openalex.org/W2770890514","doi":"https://doi.org/10.1109/taslp.2017.2759002","mag":"2770890514","pmid":"https://pubmed.ncbi.nlm.nih.gov/33748320"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2759002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2759002","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://www.ncbi.nlm.nih.gov/pmc/articles/7971071","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073341046","display_name":"Michal Borsk\u00fd","orcid":"https://orcid.org/0000-0001-7908-5411"},"institutions":[{"id":"https://openalex.org/I123185442","display_name":"Reykjav\u00edk University","ror":"https://ror.org/05d2kyx68","country_code":"IS","type":"education","lineage":["https://openalex.org/I123185442"]}],"countries":["IS"],"is_corresponding":true,"raw_author_name":"Michal Borsky","raw_affiliation_strings":["School of Science and Engineering, Haskolinn i Reykjavik, Iceland"],"raw_orcid":"https://orcid.org/0000-0001-7908-5411","affiliations":[{"raw_affiliation_string":"School of Science and Engineering, Haskolinn i Reykjavik, Iceland","institution_ids":["https://openalex.org/I123185442"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006768065","display_name":"Daryush D. Mehta","orcid":"https://orcid.org/0000-0002-6535-573X"},"institutions":[{"id":"https://openalex.org/I4210087915","display_name":"Massachusetts General Hospital","ror":"https://ror.org/002pd6e78","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210087915","https://openalex.org/I48633490"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daryush D. Mehta","raw_affiliation_strings":["Massachusetts General Hospital, Center for Laryngeal Surgery and Voice Rehabilitation, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6535-573X","affiliations":[{"raw_affiliation_string":"Massachusetts General Hospital, Center for Laryngeal Surgery and Voice Rehabilitation, Boston, MA, USA","institution_ids":["https://openalex.org/I4210087915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045171250","display_name":"Jarrad H. Van Stan","orcid":"https://orcid.org/0000-0001-8932-3276"},"institutions":[{"id":"https://openalex.org/I4210087915","display_name":"Massachusetts General Hospital","ror":"https://ror.org/002pd6e78","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210087915","https://openalex.org/I48633490"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jarrad H. Van Stan","raw_affiliation_strings":["Massachusetts General Hospital, Center for Laryngeal Surgery and Voice Rehabilitation, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts General Hospital, Center for Laryngeal Surgery and Voice Rehabilitation, Boston, MA, USA","institution_ids":["https://openalex.org/I4210087915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079762083","display_name":"J\u00f3n Gu\u00f0nason","orcid":"https://orcid.org/0000-0001-6560-5543"},"institutions":[{"id":"https://openalex.org/I123185442","display_name":"Reykjav\u00edk University","ror":"https://ror.org/05d2kyx68","country_code":"IS","type":"education","lineage":["https://openalex.org/I123185442"]}],"countries":["IS"],"is_corresponding":false,"raw_author_name":"Jon Gudnason","raw_affiliation_strings":["School of Science and Engineering, Haskolinn i Reykjavik, Iceland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Science and Engineering, Haskolinn i Reykjavik, Iceland","institution_ids":["https://openalex.org/I123185442"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5073341046"],"corresponding_institution_ids":["https://openalex.org/I123185442"],"apc_list":null,"apc_paid":null,"fwci":0.7796,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.73333441,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"25","issue":"12","first_page":"2281","last_page":"2291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":1.0,"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":1.0,"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":0.9994000196456909,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7397744655609131},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7231821417808533},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6728243827819824},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6525333523750305},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5894024968147278},{"id":"https://openalex.org/keywords/breathy-voice","display_name":"Breathy voice","score":0.5793525576591492},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5427733659744263},{"id":"https://openalex.org/keywords/phonation","display_name":"Phonation","score":0.5106390118598938},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5064812898635864},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4797576665878296},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4721044600009918},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.4598369002342224},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4427313208580017},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3659721314907074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.361259788274765}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7397744655609131},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7231821417808533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6728243827819824},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6525333523750305},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5894024968147278},{"id":"https://openalex.org/C72453395","wikidata":"https://www.wikidata.org/wiki/Q3328163","display_name":"Breathy voice","level":3,"score":0.5793525576591492},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5427733659744263},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.5106390118598938},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5064812898635864},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4797576665878296},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4721044600009918},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.4598369002342224},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4427313208580017},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3659721314907074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.361259788274765},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2017.2759002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2759002","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:33748320","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33748320","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:7971071","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7971071","pdf_url":null,"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:7971071","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7971071","pdf_url":null,"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":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.5099999904632568}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321020","display_name":"Icelandic Centre for Research","ror":"https://ror.org/03srneg48"},{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W135310501","https://openalex.org/W144053593","https://openalex.org/W157162884","https://openalex.org/W1574850502","https://openalex.org/W1924962846","https://openalex.org/W1964061458","https://openalex.org/W1967553037","https://openalex.org/W1968336462","https://openalex.org/W1969940259","https://openalex.org/W1994997260","https://openalex.org/W1996962916","https://openalex.org/W2002311796","https://openalex.org/W2007091724","https://openalex.org/W2011585205","https://openalex.org/W2013374607","https://openalex.org/W2019974831","https://openalex.org/W2021320575","https://openalex.org/W2031072412","https://openalex.org/W2044146058","https://openalex.org/W2051457717","https://openalex.org/W2055387057","https://openalex.org/W2061234361","https://openalex.org/W2071895941","https://openalex.org/W2084627109","https://openalex.org/W2087445608","https://openalex.org/W2088480443","https://openalex.org/W2093862051","https://openalex.org/W2095176743","https://openalex.org/W2096760972","https://openalex.org/W2113516703","https://openalex.org/W2116373735","https://openalex.org/W2117095944","https://openalex.org/W2120532276","https://openalex.org/W2122334831","https://openalex.org/W2122410667","https://openalex.org/W2129521125","https://openalex.org/W2139252078","https://openalex.org/W2140245305","https://openalex.org/W2146055542","https://openalex.org/W2147760966","https://openalex.org/W2151251521","https://openalex.org/W2153903782","https://openalex.org/W2156847899","https://openalex.org/W2161281622","https://openalex.org/W2163224754","https://openalex.org/W2289401391","https://openalex.org/W2294232014","https://openalex.org/W2295471129","https://openalex.org/W2326404756","https://openalex.org/W2396205624","https://openalex.org/W2508600834","https://openalex.org/W2942177450","https://openalex.org/W4240039969","https://openalex.org/W4285719527","https://openalex.org/W4390912420","https://openalex.org/W6605533900","https://openalex.org/W6605851058","https://openalex.org/W6680831495","https://openalex.org/W6697155323","https://openalex.org/W6697311706","https://openalex.org/W6712260262","https://openalex.org/W6860722923","https://openalex.org/W7034203491"],"related_works":["https://openalex.org/W1980838809","https://openalex.org/W2092666606","https://openalex.org/W2144536094","https://openalex.org/W3129442396","https://openalex.org/W4229676021","https://openalex.org/W4244195428","https://openalex.org/W2030224518","https://openalex.org/W4248970328","https://openalex.org/W4214654144","https://openalex.org/W2053621666"],"abstract_inverted_index":{"The":[0,21,144,172,185],"goal":[1],"of":[2,10,75,117,137,176],"this":[3],"study":[4,22],"was":[5,64,146,178,234],"to":[6,96,216],"investigate":[7],"the":[8,24,41,48,69,113,121,133,181,190,198,226,237],"performance":[9,233],"different":[11],"feature":[12,26],"types":[13],"for":[14,132,180],"voice":[15,50,71,78,103,135,222],"quality":[16,72,223],"classification":[17,145,174,232],"using":[18,112,148,168],"multiple":[19],"classifiers.":[20],"compared":[23],"COVAREP":[25,183],"set;":[27],"which":[28,162],"included":[29],"glottal":[30,53],"source":[31],"features,":[32],"frequency":[33],"warped":[34],"cepstrum":[35],"and":[36,58,101,120,142,157,197,210,220,228],"harmonic":[37,186],"model":[38,160,187],"features;":[39],"against":[40],"mel-frequency":[42],"cepstral":[43],"coefficients":[44],"(MFCCs)":[45],"computed":[46],"from":[47,73,86,225],"acoustic":[49,227],"signal,":[51],"acoustic-based":[52],"inverse":[54],"filtered":[55],"(GIF)":[56],"waveform,":[57],"electroglottographic":[59],"(EGG)":[60],"waveform.":[61,239],"Our":[62],"hypothesis":[63],"that":[65,208],"MFCCs":[66,200],"can":[67],"capture":[68],"perceived":[70],"either":[74],"these":[76],"three":[77],"signals.":[79],"Experiments":[80],"were":[81,94,106,123,163,189,214],"carried":[82],"out":[83],"on":[84],"recordings":[85],"28":[87],"participants":[88],"with":[89,99,194],"normal":[90],"vocal":[91],"status":[92],"who":[93],"prompted":[95,134],"sustain":[97],"vowels":[98],"modal":[100,138],"non-modal":[102],"qualities.":[104],"Recordings":[105],"rated":[107],"by":[108,236],"an":[109],"expert":[110],"listener":[111],"Consensus":[114],"Auditory-Perceptual":[115],"Evaluation":[116],"Voice":[118],"(CAPE-V),":[119],"ratings":[122],"transformed":[124],"into":[125],"a":[126,169],"dichotomous":[127],"label":[128],"(presence":[129],"or":[130],"absence)":[131],"qualities":[136],"voice,":[139],"breathiness,":[140],"strain,":[141],"roughness.":[143],"done":[147],"support":[149],"vector":[150],"machines,":[151],"random":[152],"forests,":[153],"deep":[154],"neural":[155],"networks":[156],"Gaussian":[158],"mixture":[159],"classifiers,":[161],"built":[164],"as":[165],"speaker":[166],"independent":[167],"leave-one-speaker-out":[170],"strategy.":[171],"best":[173,191],"accuracy":[175],"79.97%":[177],"achieved":[179],"full":[182],"set.":[184],"features":[188,213],"performing":[192],"subset,":[193],"78.47%":[195],"accuracy,":[196],"static+dynamic":[199],"scored":[201],"at":[202],"74.52%.":[203],"A":[204],"closer":[205],"analysis":[206],"showed":[207],"MFCC":[209,212],"dynamic":[211],"able":[215],"classify":[217],"modal,":[218],"breathy,":[219],"strained":[221],"dimensions":[224],"GIF":[229],"waveforms.":[230],"Reduced":[231],"exhibited":[235],"EGG":[238]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}