{"id":"https://openalex.org/W4296068757","doi":"https://doi.org/10.21437/interspeech.2022-421","title":"KSC2: An Industrial-Scale Open-Source Kazakh Speech Corpus","display_name":"KSC2: An Industrial-Scale Open-Source Kazakh Speech Corpus","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296068757","doi":"https://doi.org/10.21437/interspeech.2022-421"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-421","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-421","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008567170","display_name":"Saida Mussakhojayeva","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saida Mussakhojayeva","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047310084","display_name":"Yerbolat Khassanov","orcid":"https://orcid.org/0000-0001-9422-6833"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yerbolat Khassanov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5044782949","display_name":"H\u00fcseyin Atakan Varol","orcid":"https://orcid.org/0000-0002-4042-425X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huseyin Atakan Varol","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5054,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.95869811,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1367","last_page":"1371"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9929999709129333,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9929999709129333,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9068999886512756,"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","display_name":"Kazakh","score":0.8049932718276978},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6783966422080994},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5347380638122559},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5053480267524719},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4548954367637634},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45267367362976074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3763813376426697},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14749759435653687},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09216722846031189},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.09063756465911865},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07474589347839355},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.05923399329185486}],"concepts":[{"id":"https://openalex.org/C2781297163","wikidata":"https://www.wikidata.org/wiki/Q9252","display_name":"Kazakh","level":2,"score":0.8049932718276978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6783966422080994},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5347380638122559},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5053480267524719},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4548954367637634},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45267367362976074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3763813376426697},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14749759435653687},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09216722846031189},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.09063756465911865},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07474589347839355},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.05923399329185486},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-421","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-421","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:nur.nu.edu.kz:123456789/15529","is_oa":false,"landing_page_url":"https://nur.nu.edu.kz/handle/123456789/15529","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":"Proceedings of the Annual Conference of the International Speech Communication Association Interspeech","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2363093443","https://openalex.org/W4206915444","https://openalex.org/W4388766676","https://openalex.org/W2353302181","https://openalex.org/W2362181825","https://openalex.org/W2320680668","https://openalex.org/W2901624366","https://openalex.org/W2519027122","https://openalex.org/W2900953188","https://openalex.org/W2371351259"],"abstract_inverted_index":{"We":[0,34,112],"present":[1],"the":[2,72,81,133,139],"first":[3],"industrial-scale":[4],"open-source":[5],"Kazakh":[6,24,30,85,110],"speech":[7,11,25,91,119],"corpus":[8,17,26,116],"for":[9,122],"automatic":[10],"recognition":[12,92],"research":[13,121],"and":[14,28,46,51,87,144],"development.":[15],"Our":[16,53],"subsumes":[18],"two":[19],"previously":[20],"presented":[21],"corpora:":[22],"1)":[23],"(KSC)":[27],"2)":[29],"text-to-speech":[31],"2":[32],"(KazakhTTS2).":[33],"also":[35],"provide":[36],"additional":[37],"data":[38],"from":[39],"other":[40],"sources,":[41],"including":[42],"television":[43,45],"news,":[44],"radio":[47],"programs,":[48],"parliament":[49],"speeches,":[50],"podcasts.":[52],"corpus,":[54,141],"which":[55,69,124],"we":[56,137],"have":[57],"named":[58],"KSC2,":[59],"contains":[60,100],"over":[61],"a":[62,105],"thousand":[63],"hours":[64],"of":[65,74,83,135],"high-quality":[66],"transcribed":[67,79],"data,":[68],"is":[70,125],"triple":[71],"size":[73],"KSC.":[75],"KSC2":[76,140],"was":[77],"manually":[78],"with":[80,102],"help":[82],"native":[84],"speakers":[86],"validated":[88],"via":[89],"preliminary":[90],"experiments":[93],"on":[94],"various":[95],"evaluation":[96],"sets.":[97],"Moreover,":[98],"it":[99],"utterances":[101],"Kazakh-Russian":[103],"code-switching,":[104],"conversational":[106],"practice":[107],"common":[108],"among":[109],"speakers.":[111],"believe":[113],"that":[114],"our":[115],"will":[117],"facilitate":[118],"processing":[120],"Kazakh,":[123],"widely":[126],"considered":[127],"an":[128],"under-resourced":[129],"language.":[130],"To":[131],"ensure":[132],"reproducibility":[134],"experiments,":[136],"share":[138],"training":[142],"recipes,":[143],"pretrained":[145],"models.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-19T15:00:24.278416","created_date":"2025-10-10T00:00:00"}
