{"id":"https://openalex.org/W7221042909","doi":"https://doi.org/10.51885/3134-8025_jics_2026_3_5","title":"RESTORING PUNCTUATION IN AUTOMATIC SPEECH RECOGNITION FOR KAZAKH LANGUAGE","display_name":"RESTORING PUNCTUATION IN AUTOMATIC SPEECH RECOGNITION FOR KAZAKH LANGUAGE","publication_year":2026,"publication_date":"2026-09-30","ids":{"openalex":"https://openalex.org/W7221042909","doi":"https://doi.org/10.51885/3134-8025_jics_2026_3_5"},"language":"en","primary_location":{"id":"doi:10.51885/3134-8025_jics_2026_3_5","doi":"https://doi.org/10.51885/3134-8025_jics_2026_3_5","is_oa":true,"landing_page_url":"https://doi.org/10.51885/3134-8025_jics_2026_3_5","pdf_url":"https://journals.ektu.kz/jics/article/download/1739/196","source":{"id":"https://openalex.org/S7407063763","display_name":"EKTU Journal of Information and Communication Sciences","issn_l":"3134-8025","issn":["3134-8025","3134-8033"],"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EKTU Journal of Information and Communication Sciences","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://journals.ektu.kz/jics/article/download/1739/196","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021414240","display_name":"Aidana Karibayeva","orcid":"https://orcid.org/0000-0002-2023-1573","observed_orcids":["https://orcid.org/0000-0002-2023-1573"]},"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":"Aidana Karibayeva","raw_affiliation_strings":["Al-Farabi Kazakh National University"],"raw_orcid":"https://orcid.org/0000-0002-2023-1573","affiliations":[{"raw_affiliation_string":"Al-Farabi Kazakh National University","institution_ids":["https://openalex.org/I185571130"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137290561","display_name":"Oleg Myssov","orcid":"https://orcid.org/0009-0006-9609-4073","observed_orcids":["https://orcid.org/0009-0006-9609-4073"]},"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":"Oleg Myssov","raw_affiliation_strings":["Al-Farabi Kazakh National University"],"raw_orcid":"https://orcid.org/0009-0006-9609-4073","affiliations":[{"raw_affiliation_string":"Al-Farabi Kazakh National University","institution_ids":["https://openalex.org/I185571130"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5117311508","display_name":"Adina Karybayeva","orcid":"https://orcid.org/0009-0003-3297-9006","observed_orcids":["https://orcid.org/0009-0003-3297-9006"]},"institutions":[{"id":"https://openalex.org/I2801841357","display_name":"Kazakh Ablai Khan University of International Relations and World Languages","ror":"https://ror.org/02q35ve03","country_code":"KZ","type":"education","lineage":["https://openalex.org/I2801841357"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Adina Karybayeva","raw_affiliation_strings":["Kazakh Ablai Khan University of International Relations and World Languages"],"raw_orcid":"https://orcid.org/0009-0003-3297-9006","affiliations":[{"raw_affiliation_string":"Kazakh Ablai Khan University of International Relations and World Languages","institution_ids":["https://openalex.org/I2801841357"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":null,"issue":"3","first_page":"79","last_page":"79"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965999722480774,"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":0.9965999722480774,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.002199999988079071,"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/T12031","display_name":"Speech and dialogue systems","score":0.00039999998989515007,"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/punctuation-restoration","display_name":"punctuation restoration","score":0.9919999837875366},{"id":"https://openalex.org/keywords/kazakh-language","display_name":"Kazakh language","score":0.9539999961853027},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.9729999899864197},{"id":"https://openalex.org/keywords/comma","display_name":"comma","score":0.5080000162124634},{"id":"https://openalex.org/keywords/period","display_name":"period","score":0.9670000076293945},{"id":"https://openalex.org/keywords/question-marks","display_name":"question marks","score":0.9810000061988831},{"id":"https://openalex.org/keywords/exclamation-marks","display_name":"exclamation marks","score":0.9980000257492065},{"id":"https://openalex.org/keywords/code-switching","display_name":"code-switching","score":0.8939999938011169},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.5479999780654907}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.9648000001907349},{"id":"https://openalex.org/C2781297163","wikidata":"https://www.wikidata.org/wiki/Q9252","display_name":"Kazakh","level":2,"score":0.7300999760627747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6833000183105469},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5684999823570251},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5357999801635742},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5055000185966492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46459999680519104},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.4237000048160553},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.37220001220703125},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C2780343019","wikidata":"https://www.wikidata.org/wiki/Q7918","display_name":"Bulgarian","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.28200000524520874}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.51885/3134-8025_jics_2026_3_5","doi":"https://doi.org/10.51885/3134-8025_jics_2026_3_5","is_oa":true,"landing_page_url":"https://doi.org/10.51885/3134-8025_jics_2026_3_5","pdf_url":"https://journals.ektu.kz/jics/article/download/1739/196","source":{"id":"https://openalex.org/S7407063763","display_name":"EKTU Journal of Information and Communication Sciences","issn_l":"3134-8025","issn":["3134-8025","3134-8033"],"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EKTU Journal of Information and Communication Sciences","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.51885/3134-8025_jics_2026_3_5","doi":"https://doi.org/10.51885/3134-8025_jics_2026_3_5","is_oa":true,"landing_page_url":"https://doi.org/10.51885/3134-8025_jics_2026_3_5","pdf_url":"https://journals.ektu.kz/jics/article/download/1739/196","source":{"id":"https://openalex.org/S7407063763","display_name":"EKTU Journal of Information and Communication Sciences","issn_l":"3134-8025","issn":["3134-8025","3134-8033"],"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EKTU Journal of Information and Communication Sciences","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221042909.pdf","grobid_xml":"https://content.openalex.org/works/W7221042909.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2046766797","https://openalex.org/W2114252161","https://openalex.org/W2116353118","https://openalex.org/W2169187092","https://openalex.org/W2398104528","https://openalex.org/W2513522215","https://openalex.org/W2626778328","https://openalex.org/W2810621157","https://openalex.org/W2913345884","https://openalex.org/W2963341956","https://openalex.org/W3009096638","https://openalex.org/W3037101098","https://openalex.org/W3106905592","https://openalex.org/W3183246637","https://openalex.org/W3185113268","https://openalex.org/W3204295894","https://openalex.org/W4280556124","https://openalex.org/W4387913150","https://openalex.org/W4415424121","https://openalex.org/W4415523994"],"related_works":["https://openalex.org/W7213502099","https://openalex.org/W7162676962","https://openalex.org/W3037230560","https://openalex.org/W4410544727","https://openalex.org/W4210452164","https://openalex.org/W7140079101","https://openalex.org/W4386429885","https://openalex.org/W4385822993","https://openalex.org/W2573354089","https://openalex.org/W7219585980"],"abstract_inverted_index":{"This":[0],"paper":[1],"considers":[2],"the":[3,22,40,57,69,72,99,119,160,164,174],"problem":[4,25],"of":[5,60,107,126],"punctuation":[6,23,32,100,111],"restoration":[7,24,101],"in":[8,26,63],"Kazakh":[9,27,50],"automatic":[10],"speech":[11],"recognition":[12],"(ASR)":[13],"systems.":[14],"The":[15],"proposed":[16],"approach":[17],"demonstrates":[18],"a":[19,78,104,143],"solution":[20],"to":[21,151,157,169],"ASR":[28,65],"for":[29,109,128,131,135,139],"four":[30,110],"main":[31,175],"classes":[33,112],"(COMMA,":[34,113],"PERIOD,":[35,114],"QUESTION,":[36,115],"and":[37,39,52,74,93,116,137],"EXCLAMATION)":[38,117],"unpunctuated":[41],"class":[42,162],"(O).":[43],"Experiments":[44,96],"were":[45],"conducted":[46],"on":[47,118],"both":[48,85],"monolingual":[49,120],"texts":[51],"mixed":[53],"Kazakh-Russian":[54],"data,":[55],"covering":[56],"practical":[58],"parameters":[59],"multilingual":[61],"communication":[62],"modern":[64],"applications.":[66],"To":[67],"reduce":[68],"imbalance":[70],"between":[71],"exclamation":[73,140,161],"question":[75,132],"mark":[76],"classes,":[77],"specially":[79],"labeled":[80],"corpus":[81],"was":[82],"created":[83],"using":[84],"real":[86],"sentences":[87,150],"collected":[88],"from":[89,155],"open":[90],"Kazakh-language":[91],"sources":[92],"LLM-assisted":[94],"paraphrasing.":[95],"showed":[97],"that":[98],"model":[102],"achieved":[103],"macro-F1":[105,154],"score":[106],"93.23%":[108],"test":[121,146],"set,":[122,147],"with":[123],"F1":[124],"scores":[125],"98.99%":[127],"period,":[129],"94.35%":[130],"mark,":[133],"87.77%":[134],"comma,":[136],"91.82%":[138],"mark.":[141],"On":[142],"held-out":[144],"code-switching":[145],"adding":[148],"code-switched":[149],"training":[152],"raised":[153],"32.81%":[156],"63.88%,":[158],"though":[159],"remains":[163],"weakest":[165],"(26.47%":[166],"F1),":[167],"pointing":[168],"prosody-free":[170],"intonation":[171],"cues":[172],"as":[173],"remaining":[176],"challenge.":[177]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-09T00:00:00"}
