{"id":"https://openalex.org/W4404900640","doi":"https://doi.org/10.37943/20dzgh8448","title":"KAZAKH SPEECH AND RECOGNITION METHODS: ERROR ANALYSIS AND IMPROVEMENT PROSPECTS","display_name":"KAZAKH SPEECH AND RECOGNITION METHODS: ERROR ANALYSIS AND IMPROVEMENT PROSPECTS","publication_year":2024,"publication_date":"2024-10-30","ids":{"openalex":"https://openalex.org/W4404900640","doi":"https://doi.org/10.37943/20dzgh8448"},"language":"en","primary_location":{"id":"doi:10.37943/20dzgh8448","doi":"https://doi.org/10.37943/20dzgh8448","is_oa":true,"landing_page_url":"https://doi.org/10.37943/20dzgh8448","pdf_url":"https://journal.astanait.edu.kz/index.php/ojs/article/download/649/222","source":{"id":"https://openalex.org/S4210225114","display_name":"Scientific Journal of Astana IT University","issn_l":"2707-9031","issn":["2707-9031","2707-904X"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj","erih-plus"],"host_organization":"https://openalex.org/I4405257690","host_organization_name":"Astana IT University","host_organization_lineage":["https://openalex.org/I4405257690"],"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":"Scientific Journal of Astana IT University","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://journal.astanait.edu.kz/index.php/ojs/article/download/649/222","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114942387","display_name":"Yerlan Karabaliyev","orcid":"https://orcid.org/0009-0001-9465-3998","observed_orcids":["https://orcid.org/0009-0001-9465-3998"]},"institutions":[{"id":"https://openalex.org/I4210143508","display_name":"International Information Technologies University","ror":"https://ror.org/042dtza69","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4210143508"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Yerlan Karabaliyev","raw_affiliation_strings":["International Information Technology University, Kazakhstan"],"raw_orcid":"https://orcid.org/0009-0001-9465-3998","affiliations":[{"raw_affiliation_string":"International Information Technology University, Kazakhstan","institution_ids":["https://openalex.org/I4210143508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025169518","display_name":"Kateryna V. Kolesnikova","orcid":"https://orcid.org/0000-0002-9160-5982","observed_orcids":["https://orcid.org/0000-0002-9160-5982"]},"institutions":[{"id":"https://openalex.org/I4210143508","display_name":"International Information Technologies University","ror":"https://ror.org/042dtza69","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4210143508"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Kateryna Kolesnikova","raw_affiliation_strings":["International Information Technology University, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0002-9160-5982","affiliations":[{"raw_affiliation_string":"International Information Technology University, Kazakhstan","institution_ids":["https://openalex.org/I4210143508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210143508"],"apc_list":null,"apc_paid":null,"fwci":0.9086,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75387672,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"62","last_page":"75"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":0.0,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.0,"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/kazakh-language","display_name":"Kazakh language","score":0.9449999928474426},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.9490000009536743},{"id":"https://openalex.org/keywords/error-analysis","display_name":"error analysis","score":0.6660000085830688},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"word error rate","score":0.8859999775886536},{"id":"https://openalex.org/keywords/vowel-harmony","display_name":"vowel harmony","score":0.9700000286102295},{"id":"https://openalex.org/keywords/regional-dialects","display_name":"regional dialects","score":0.7540000081062317},{"id":"https://openalex.org/keywords/agglutinative-morphology","display_name":"agglutinative morphology","score":0.9369999766349792},{"id":"https://openalex.org/keywords/kaldi","display_name":"Kaldi","score":0.7879999876022339},{"id":"https://openalex.org/keywords/phoneme-recognition","display_name":"phoneme recognition","score":0.48500001430511475},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.628000020980835},{"id":"https://openalex.org/keywords/acoustic-model-adaptation","display_name":"acoustic model adaptation","score":0.5929999947547913}],"concepts":[{"id":"https://openalex.org/C2781297163","wikidata":"https://www.wikidata.org/wiki/Q9252","display_name":"Kazakh","level":2,"score":0.8736225366592407},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6914944648742676},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5467650890350342},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.5217562317848206},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44680020213127136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3960499167442322},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3882204294204712},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21835491061210632},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20379570126533508},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.054362982511520386},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.37943/20dzgh8448","doi":"https://doi.org/10.37943/20dzgh8448","is_oa":true,"landing_page_url":"https://doi.org/10.37943/20dzgh8448","pdf_url":"https://journal.astanait.edu.kz/index.php/ojs/article/download/649/222","source":{"id":"https://openalex.org/S4210225114","display_name":"Scientific Journal of Astana IT University","issn_l":"2707-9031","issn":["2707-9031","2707-904X"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj","erih-plus"],"host_organization":"https://openalex.org/I4405257690","host_organization_name":"Astana IT University","host_organization_lineage":["https://openalex.org/I4405257690"],"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":"Scientific Journal of Astana IT University","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a34cf000a57345fa8d53b66feb78b3c3","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/a34cf000a57345fa8d53b66feb78b3c3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scientific Journal of Astana IT University, Vol 20 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.37943/20dzgh8448","doi":"https://doi.org/10.37943/20dzgh8448","is_oa":true,"landing_page_url":"https://doi.org/10.37943/20dzgh8448","pdf_url":"https://journal.astanait.edu.kz/index.php/ojs/article/download/649/222","source":{"id":"https://openalex.org/S4210225114","display_name":"Scientific Journal of Astana IT University","issn_l":"2707-9031","issn":["2707-9031","2707-904X"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj","erih-plus"],"host_organization":"https://openalex.org/I4405257690","host_organization_name":"Astana IT University","host_organization_lineage":["https://openalex.org/I4405257690"],"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":"Scientific Journal of Astana IT University","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404900640.pdf","grobid_xml":"https://content.openalex.org/works/W4404900640.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W3088421464","https://openalex.org/W3142872754","https://openalex.org/W3184165979","https://openalex.org/W3197964296","https://openalex.org/W3204295894","https://openalex.org/W4220689448"],"related_works":["https://openalex.org/W4409801229","https://openalex.org/W7220620392","https://openalex.org/W7169130945","https://openalex.org/W4415052592","https://openalex.org/W2943142297","https://openalex.org/W4389960174","https://openalex.org/W7159835300","https://openalex.org/W4405112657","https://openalex.org/W7163705595","https://openalex.org/W4407225214"],"abstract_inverted_index":{"This":[0,81,226],"study":[1,82],"offers":[2],"a":[3,55,71,159,230],"detailed":[4],"evaluation":[5],"of":[6,47,58,73,76,124,133,161,250],"automatic":[7],"speech":[8,224],"recognition":[9],"(ASR)":[10],"systems":[11,62,135,215,248],"for":[12,35,140,232,243],"the":[13,20,27,45,78,85,96,125,129,134,213],"Kazakh,":[14],"examining":[15],"their":[16],"performance":[17],"in":[18,145],"recognizing":[19,146],"phonetic":[21,173],"and":[22,44,67,102,105,117,150,174,180,189,198,222,237],"linguistic":[23,205],"features":[24],"unique":[25],"to":[26,38,169,202],"language.":[28],"The":[29],"Kazakh":[30,79,234],"language":[31],"presents":[32],"specific":[33],"challenges":[34],"ASR":[36,61,214,235,247],"due":[37],"its":[39],"complex":[40,219],"phonology,":[41],"vowel":[42,115],"harmony,":[43],"presence":[46],"multiple":[48],"regional":[49,223],"dialects.":[50],"To":[51,155],"address":[52],"these":[53,157,211],"challenges,":[54],"comparative":[56],"analysis":[57],"three":[59],"leading":[60],"were":[63],"conducted\u2014Kaldi,":[64],"Mozilla":[65,106],"DeepSpeech,":[66],"Google":[68,121],"Speech-to-Text":[69,122],"API\u2014using":[70],"dataset":[72,200],"101":[74],"recordings":[75],"spoken":[77],"text.":[80],"focuses":[83],"on":[84],"systems'":[86],"word":[87],"error":[88],"rates":[89],"(WER),":[90],"identifying":[91],"common":[92],"misrecognitions,":[93],"especially":[94],"with":[95,113],"Kazakh-specific":[97],"phonemes":[98],"like":[99],"\"\u049b,\"":[100],"\"\u04a3,\"":[101],"\"\u04af.\"":[103],"Kaldi":[104],"DeepSpeech":[107],"exhibited":[108],"high":[109],"WERs,":[110],"particularly":[111],"struggling":[112],"Kazakh\u2019s":[114,147,172,204],"harmony":[116],"consonant":[118],"distinctions,":[119],"while":[120],"achieved":[123],"lowest":[126],"WER":[127],"among":[128],"three.":[130],"However,":[131],"none":[132],"demonstrated":[136],"accuracy":[137],"levels":[138],"sufficient":[139],"practical":[141],"applications,":[142],"as":[143,186],"errors":[144],"agglutinative":[148],"morphology":[149],"case":[151],"endings":[152],"remained":[153],"pervasive.":[154],"improve":[156],"outcomes,":[158],"series":[160],"enhancements":[162],"are":[163,241],"proposed,":[164],"including":[165],"adapting":[166],"acoustic":[167],"models":[168],"better":[170,217],"reflect":[171],"morphological":[175],"traits,":[176],"integrating":[177],"dialect-specific":[178],"data,":[179],"employing":[181],"machine":[182],"learning":[183,188],"methods":[184],"such":[185],"transfer":[187],"hybrid":[190],"models.":[191],"Additional":[192],"steps":[193],"include":[194],"refining":[195],"data":[196],"preprocessing":[197],"increasing":[199],"diversity":[201],"capture":[203],"nuances":[206],"more":[207],"accurately.":[208],"By":[209],"addressing":[210],"limitations,":[212],"can":[216],"handle":[218],"sentence":[220],"structures":[221],"variations.":[225],"research":[227],"thus":[228],"provides":[229],"foundation":[231],"advancing":[233],"technologies":[236],"contributes":[238],"insights":[239],"that":[240],"vital":[242],"developing":[244],"inclusive,":[245],"effective":[246],"capable":[249],"supporting":[251],"linguistically":[252],"diverse":[253],"users.":[254]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2024-12-02T00:00:00"}
