{"id":"https://openalex.org/W4384928248","doi":"https://doi.org/10.3390/bdcc7030132","title":"The Development of a Kazakh Speech Recognition Model Using a Convolutional Neural Network with Fixed Character Level Filters","display_name":"The Development of a Kazakh Speech Recognition Model Using a Convolutional Neural Network with Fixed Character Level Filters","publication_year":2023,"publication_date":"2023-07-20","ids":{"openalex":"https://openalex.org/W4384928248","doi":"https://doi.org/10.3390/bdcc7030132"},"language":"en","primary_location":{"id":"doi:10.3390/bdcc7030132","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc7030132","pdf_url":"https://www.mdpi.com/2504-2289/7/3/132/pdf?version=1689830879","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-2289/7/3/132/pdf?version=1689830879","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067474890","display_name":"Nurgali Kadyrbek","orcid":"https://orcid.org/0000-0002-5461-8899"},"institutions":[{"id":"https://openalex.org/I185571130","display_name":"Al-Farabi Kazakh National University","ror":"https://ror.org/03q0vrn42","country_code":"KZ","type":"education","lineage":["https://openalex.org/I185571130"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Nurgali Kadyrbek","raw_affiliation_strings":["Department of AI & Big Data, Faculty of Information Technologies, Al-Farabi Kazakh National University, Al-Farabi Ave., 71, Almaty 050040, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of AI & Big Data, Faculty of Information Technologies, Al-Farabi Kazakh National University, Al-Farabi Ave., 71, Almaty 050040, Kazakhstan","institution_ids":["https://openalex.org/I185571130"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049620410","display_name":"\u041c\u0430\u0434\u0438\u043d\u0430 \u041c\u0430\u043d\u0441\u0443\u0440\u043e\u0432\u0430","orcid":"https://orcid.org/0000-0002-9680-2758"},"institutions":[{"id":"https://openalex.org/I185571130","display_name":"Al-Farabi Kazakh National University","ror":"https://ror.org/03q0vrn42","country_code":"KZ","type":"education","lineage":["https://openalex.org/I185571130"]}],"countries":["KZ"],"is_corresponding":true,"raw_author_name":"Madina Mansurova","raw_affiliation_strings":["Department of AI & Big Data, Faculty of Information Technologies, Al-Farabi Kazakh National University, Al-Farabi Ave., 71, Almaty 050040, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of AI & Big Data, Faculty of Information Technologies, Al-Farabi Kazakh National University, Al-Farabi Ave., 71, Almaty 050040, Kazakhstan","institution_ids":["https://openalex.org/I185571130"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067593236","display_name":"Adai Shomanov","orcid":"https://orcid.org/0000-0001-8253-7474"},"institutions":[{"id":"https://openalex.org/I60559429","display_name":"Nazarbayev University","ror":"https://ror.org/052bx8q98","country_code":"KZ","type":"education","lineage":["https://openalex.org/I60559429"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Adai Shomanov","raw_affiliation_strings":["School of Engineering and Digital Sciences, Nazarbayev University, Kabanbai Batyr Ave., 53, Astana 010000, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering and Digital Sciences, Nazarbayev University, Kabanbai Batyr Ave., 53, Astana 010000, Kazakhstan","institution_ids":["https://openalex.org/I60559429"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022878344","display_name":"Gaukhar Makharova","orcid":"https://orcid.org/0000-0003-4701-0073"},"institutions":[{"id":"https://openalex.org/I185571130","display_name":"Al-Farabi Kazakh National University","ror":"https://ror.org/03q0vrn42","country_code":"KZ","type":"education","lineage":["https://openalex.org/I185571130"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Gaukhar Makharova","raw_affiliation_strings":["Department of Foreign Language, Faculty of Philology, Al-Farabi Kazakh National University, Almaty 050040, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Foreign Language, Faculty of Philology, Al-Farabi Kazakh National University, Almaty 050040, Kazakhstan","institution_ids":["https://openalex.org/I185571130"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049620410"],"corresponding_institution_ids":["https://openalex.org/I185571130"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":1.4224,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84723886,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"7","issue":"3","first_page":"132","last_page":"132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9958000183105469,"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/T11309","display_name":"Music and Audio Processing","score":0.9937999844551086,"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":0.8172674179077148},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6871217489242554},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5253307819366455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49865150451660156},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4926162362098694},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46962761878967285},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4612054228782654},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4483187198638916},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.43983617424964905},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.4103706479072571},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3785986304283142},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3111244738101959},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09180566668510437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8172674179077148},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6871217489242554},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5253307819366455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49865150451660156},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4926162362098694},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46962761878967285},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4612054228782654},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4483187198638916},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.43983617424964905},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.4103706479072571},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3785986304283142},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3111244738101959},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09180566668510437},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/bdcc7030132","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc7030132","pdf_url":"https://www.mdpi.com/2504-2289/7/3/132/pdf?version=1689830879","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},{"id":"pmh:oai:nur.nu.edu.kz:123456789/16459","is_oa":false,"landing_page_url":"https://nur.nu.edu.kz/handle/123456789/16459","pdf_url":null,"source":{"id":"https://openalex.org/S4377196417","display_name":"Nazarbayev University Repository (Nazarbayev University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60559429","host_organization_name":"Nazarbayev University","host_organization_lineage":["https://openalex.org/I60559429"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:033bc83af3f74f90bd379a9a4d275969","is_oa":true,"landing_page_url":"https://doaj.org/article/033bc83af3f74f90bd379a9a4d275969","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,"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":"Big Data and Cognitive Computing, Vol 7, Iss 3, p 132 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2504-2289/7/3/132/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/bdcc7030132","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data and Cognitive Computing; Volume 7; Issue 3; Pages: 132","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/bdcc7030132","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc7030132","pdf_url":"https://www.mdpi.com/2504-2289/7/3/132/pdf?version=1689830879","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4384928248.pdf"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2160815625","https://openalex.org/W2931104117","https://openalex.org/W3004196347","https://openalex.org/W3100732527","https://openalex.org/W3126471189","https://openalex.org/W3132813756","https://openalex.org/W3184165979","https://openalex.org/W3210365128","https://openalex.org/W3212880672","https://openalex.org/W4200510322","https://openalex.org/W4205130185","https://openalex.org/W4206915444","https://openalex.org/W4221152574","https://openalex.org/W4285733490","https://openalex.org/W4289524424","https://openalex.org/W4315786723","https://openalex.org/W6791261095","https://openalex.org/W6841391687"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W2594897229","https://openalex.org/W4221142855","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W4290708361","https://openalex.org/W2126322296","https://openalex.org/W2129812225","https://openalex.org/W2244609359"],"abstract_inverted_index":{"This":[0],"study":[1,229],"is":[2],"devoted":[3],"to":[4,23,106,143,209,244],"the":[5,11,24,28,35,40,65,78,101,114,131,134,145,185,188,197],"transcription":[6],"of":[7,27,42,59,64,67,83,85,103,133,159,173,187],"human":[8],"speech":[9,47,237],"in":[10,14,33,180,184],"Kazakh":[12,29],"language":[13],"dynamically":[15],"changing":[16],"conditions.":[17],"It":[18],"discusses":[19],"key":[20],"aspects":[21],"related":[22,105],"phonetic":[25],"structure":[26],"language,":[30],"technical":[31],"considerations":[32],"collecting":[34],"transcribed":[36],"audio":[37,52,233],"corpus,":[38,234],"and":[39,69,81,94,126,164,175,240,247],"use":[41],"deep":[43],"neural":[44],"networks":[45],"for":[46,100,162],"modeling.":[48],"A":[49],"high-quality":[50,232],"decoded":[51],"corpus":[53,89],"was":[54],"collected,":[55],"containing":[56],"554":[57],"h":[58],"data,":[60],"giving":[61],"an":[62,123,235],"idea":[63],"frequencies":[66],"letters":[68],"syllables,":[70],"as":[71,73,77,96],"well":[72],"demographic":[74],"parameters":[75],"such":[76],"gender,":[79],"age,":[80],"region":[82],"residence":[84],"native":[86],"speakers.":[87],"The":[88,153,167,194,217],"contains":[90],"a":[91,97,119,171,181,201,231],"universal":[92],"vocabulary":[93],"serves":[95],"valuable":[98],"resource":[99],"development":[102],"modules":[104],"speech.":[107],"Machine":[108],"learning":[109,177],"experiments":[110],"were":[111,141],"conducted":[112],"using":[113,170],"DeepSpeech2":[115],"model,":[116,135,239],"which":[117],"includes":[118],"sequence-to-sequence":[120],"architecture":[121,219],"with":[122,138,224],"encoder,":[124],"decoder,":[125],"attention":[127],"mechanism.":[128],"To":[129],"increase":[130],"reliability":[132],"filters":[136,161],"initialized":[137],"symbol-level":[139],"embeddings":[140],"introduced":[142],"reduce":[144],"dependence":[146],"on":[147,150,196,222],"accurate":[148],"positioning":[149],"object":[151],"maps.":[152],"training":[154],"process":[155],"included":[156],"simultaneous":[157],"preparation":[158],"convolutional":[160],"spectrograms":[163],"symbolic":[165],"objects.":[166],"proposed":[168,218],"approach,":[169],"combination":[172],"supervised":[174],"unsupervised":[176],"methods,":[178],"resulted":[179],"66.7%":[182],"reduction":[183],"weight":[186],"model":[189],"while":[190],"maintaining":[191],"relative":[192],"accuracy.":[193],"evaluation":[195],"test":[198],"sample":[199],"showed":[200],"7.6%":[202],"lower":[203],"character":[204],"error":[205],"rate":[206],"(CER)":[207],"compared":[208],"existing":[210],"models,":[211],"demonstrating":[212],"its":[213],"most":[214],"modern":[215],"characteristics.":[216],"provides":[220],"deployment":[221],"platforms":[223],"limited":[225],"resources.":[226],"Overall,":[227],"this":[228],"presents":[230],"improved":[236],"recognition":[238],"promising":[241],"results":[242],"applicable":[243],"speech-related":[245],"applications":[246],"languages":[248],"beyond":[249],"Kazakh.":[250]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5}],"updated_date":"2026-08-10T07:06:39.071514","created_date":"2023-07-22T00:00:00"}