{"id":"https://openalex.org/W7225081763","doi":"https://doi.org/10.52167/1609-1817-2026-4-145-440-453","title":"SPEECH IMPAIRMENT DETECTION AND ANALYSIS USING WAV2VEC2 AND \u0410UTOENCODER","display_name":"SPEECH IMPAIRMENT DETECTION AND ANALYSIS USING WAV2VEC2 AND \u0410UTOENCODER","publication_year":2026,"publication_date":"2026-08-31","ids":{"openalex":"https://openalex.org/W7225081763","doi":"https://doi.org/10.52167/1609-1817-2026-4-145-440-453"},"language":"en","primary_location":{"id":"doi:10.52167/1609-1817-2026-4-145-440-453","doi":"https://doi.org/10.52167/1609-1817-2026-4-145-440-453","is_oa":true,"landing_page_url":"https://doi.org/10.52167/1609-1817-2026-4-145-440-453","pdf_url":"https://vestnik.alt.edu.kz/index.php/journal/article/download/3265/1974","source":{"id":"https://openalex.org/S4210207685","display_name":"\u0412\u0435\u0441\u0442\u043d\u0438\u043a \u041a\u0430\u0437\u0410\u0422\u041a","issn_l":"1609-1817","issn":["1609-1817","2790-5802"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4387930291","host_organization_name":"Mukhametzhan Tynyshbayev ALT University","host_organization_lineage":["https://openalex.org/I4387930291"],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"\u0412\u0435\u0441\u0442\u043d\u0438\u043a \u041a\u0430\u0437\u0410\u0422\u041a","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://vestnik.alt.edu.kz/index.php/journal/article/download/3265/1974","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058034924","display_name":"Gulnur Kazbekova","orcid":"https://orcid.org/0000-0002-2756-7926","observed_orcids":["https://orcid.org/0000-0002-2756-7926"]},"institutions":[{"id":"https://openalex.org/I2801707353","display_name":"Ahmet Yesevi University","ror":"https://ror.org/01gtvs751","country_code":"KZ","type":"education","lineage":["https://openalex.org/I2801707353"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Gulnur Kazbekova","raw_affiliation_strings":["Department of Computer Engineering , Khoja Akhmet Yassawi International Kazakh-Turkish University , Kazakhstan,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering , Khoja Akhmet Yassawi International Kazakh-Turkish University , Kazakhstan,","institution_ids":["https://openalex.org/I2801707353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115577896","display_name":"Arypzhan Aben","orcid":"https://orcid.org/0000-0001-8534-3288","observed_orcids":["https://orcid.org/0000-0001-8534-3288"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arypzhan Aben","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113061460","display_name":"Zhuldyz Ismagulova","orcid":"https://orcid.org/0000-0002-0979-0243","observed_orcids":["https://orcid.org/0000-0002-0979-0243"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuldyz Ismagulova","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5160370164","display_name":"Aigerim Sultanali","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aigerim Sultanali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":"145","first_page":"440","last_page":"453"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.7505000233650208,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.7505000233650208,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.22310000658035278,"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":0.01899999938905239,"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/dysarthria","display_name":"dysarthria","score":0.8339999914169312},{"id":"https://openalex.org/keywords/wav2vec-2-0","display_name":"wav2vec 2.0","score":0.9440000057220459},{"id":"https://openalex.org/keywords/autoencoder","display_name":"autoencoder","score":0.8820000290870667},{"id":"https://openalex.org/keywords/reconstruction-error","display_name":"reconstruction error","score":0.718999981880188},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"anomaly detection","score":0.718999981880188},{"id":"https://openalex.org/keywords/formant-frequencies","display_name":"formant frequencies","score":0.847000002861023},{"id":"https://openalex.org/keywords/speech-acoustics","display_name":"speech acoustics","score":0.5950000286102295},{"id":"https://openalex.org/keywords/speech-monitoring","display_name":"speech monitoring","score":0.7919999957084656}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6460000276565552},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5805000066757202},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.5723999738693237},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5206999778747559},{"id":"https://openalex.org/C2779642007","wikidata":"https://www.wikidata.org/wiki/Q1282114","display_name":"Speech disorder","level":2,"score":0.4609000086784363},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42010000348091125},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.41760000586509705},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.34540000557899475},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C122048520","wikidata":"https://www.wikidata.org/wiki/Q2913954","display_name":"Percentile","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3061000108718872},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.26190000772476196},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.52167/1609-1817-2026-4-145-440-453","doi":"https://doi.org/10.52167/1609-1817-2026-4-145-440-453","is_oa":true,"landing_page_url":"https://doi.org/10.52167/1609-1817-2026-4-145-440-453","pdf_url":"https://vestnik.alt.edu.kz/index.php/journal/article/download/3265/1974","source":{"id":"https://openalex.org/S4210207685","display_name":"\u0412\u0435\u0441\u0442\u043d\u0438\u043a \u041a\u0430\u0437\u0410\u0422\u041a","issn_l":"1609-1817","issn":["1609-1817","2790-5802"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4387930291","host_organization_name":"Mukhametzhan Tynyshbayev ALT University","host_organization_lineage":["https://openalex.org/I4387930291"],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"\u0412\u0435\u0441\u0442\u043d\u0438\u043a \u041a\u0430\u0437\u0410\u0422\u041a","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.52167/1609-1817-2026-4-145-440-453","doi":"https://doi.org/10.52167/1609-1817-2026-4-145-440-453","is_oa":true,"landing_page_url":"https://doi.org/10.52167/1609-1817-2026-4-145-440-453","pdf_url":"https://vestnik.alt.edu.kz/index.php/journal/article/download/3265/1974","source":{"id":"https://openalex.org/S4210207685","display_name":"\u0412\u0435\u0441\u0442\u043d\u0438\u043a \u041a\u0430\u0437\u0410\u0422\u041a","issn_l":"1609-1817","issn":["1609-1817","2790-5802"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4387930291","host_organization_name":"Mukhametzhan Tynyshbayev ALT University","host_organization_lineage":["https://openalex.org/I4387930291"],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"\u0412\u0435\u0441\u0442\u043d\u0438\u043a \u041a\u0430\u0437\u0410\u0422\u041a","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.46810001134872437,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225081763.pdf","grobid_xml":"https://content.openalex.org/works/W7225081763.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W4402221087","https://openalex.org/W4411487658"],"related_works":["https://openalex.org/W4372338196","https://openalex.org/W7155042308","https://openalex.org/W2293957671","https://openalex.org/W4391825007","https://openalex.org/W2577849124","https://openalex.org/W7138920180","https://openalex.org/W2913950396","https://openalex.org/W2961221611","https://openalex.org/W4297841331","https://openalex.org/W395673888"],"abstract_inverted_index":{"Speech":[0],"disorders":[1,200],"can":[2,184],"affect":[3],"communication":[4],"and":[5,10,54,69,105,189,197,215],"may":[6,19],"interfere":[7],"with":[8,46,144,181,194],"learning":[9],"everyday":[11],"social":[12],"interaction.":[13],"Automatic":[14],"analysis":[15,122,183],"of":[16,75,85,95,123,164],"disordered":[17],"speech":[18,62,97,107,147,199],"provide":[20],"additional":[21],"information":[22],"for":[23,212],"identifying":[24],"acoustic":[25],"changes":[26,128,157],"that":[27,177],"are":[28,201,209],"difficult":[29],"to":[30,49,158,203],"examine":[31,50],"consistently":[32],"through":[33],"perceptual":[34],"assessment":[35],"alone.":[36,173],"In":[37],"this":[38],"study,":[39],"a":[40,71],"pretrained":[41],"Wav2Vec2":[42,178],"model":[43],"was":[44,59,92],"combined":[45,180],"an":[47,165],"autoencoder":[48,58],"differences":[51,99,186,208],"between":[52,103,187],"control":[53,67,90,104,188],"dysarthric":[55,96,190],"speech.":[56,191],"The":[57,77,149],"trained":[60],"on":[61],"representations":[63,179],"obtained":[64],"from":[65,81],"the":[66,82,89,110,118,145,170,206],"group":[68],"reached":[70],"reconstruction":[72,86,101],"error":[73,102],"(MSE)":[74],"0.0008.":[76],"anomaly":[78,113],"threshold,":[79],"calculated":[80],"99th":[83],"percentile":[84],"errors":[87],"in":[88,100,129,153],"samples,":[91],"0.002143.":[93],"Analysis":[94],"showed":[98,127],"affected":[106],"segments,":[108],"although":[109],"highest":[111],"observed":[112,207],"value":[114],"(0.001831)":[115],"remained":[116],"below":[117],"selected":[119],"threshold.":[120],"Acoustic":[121],"these":[124],"segments":[125],"also":[126],"formant":[130],"frequencies.":[131],"F1":[132],"increased":[133],"by":[134,140],"approximately":[135],"35\u201340%,":[136],"while":[137],"F2":[138],"decreased":[139],"about":[141],"20\u201330%":[142],"compared":[143],"reference":[146],"samples.":[148],"recordings":[150],"were":[151],"analyzed":[152],"0.5-second":[154],"windows,":[155],"allowing":[156],"be":[159],"examined":[160],"within":[161],"individual":[162],"parts":[163],"utterance":[166],"rather":[167],"than":[168],"at":[169],"recording":[171],"level":[172],"These":[174],"results":[175],"show":[176],"reconstruction-based":[182],"capture":[185],"Further":[192],"experiments":[193],"more":[195],"speakers":[196],"different":[198],"required":[202],"determine":[204],"whether":[205],"sufficiently":[210],"consistent":[211],"automatic":[213],"screening":[214],"speech-monitoring":[216],"applications.":[217]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-11-03T00:00:00"}