{"id":"https://openalex.org/W3155727213","doi":"https://doi.org/10.21437/interspeech.2021-2124","title":"KazakhTTS: An Open-Source Kazakh Text-to-Speech Synthesis Dataset","display_name":"KazakhTTS: An Open-Source Kazakh Text-to-Speech Synthesis Dataset","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3155727213","doi":"https://doi.org/10.21437/interspeech.2021-2124","mag":"3155727213"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-2124","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.08459","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008567170","display_name":"Saida Mussakhojayeva","orcid":null},"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":true,"raw_author_name":"Saida Mussakhojayeva","raw_affiliation_strings":["Institute of Smart Systems and Artificial Intelligence (ISSAI), Nazarbayev University, Nur-Sultan, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Smart Systems and Artificial Intelligence (ISSAI), Nazarbayev University, Nur-Sultan, Kazakhstan","institution_ids":["https://openalex.org/I60559429"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059183363","display_name":"Aigerim Janaliyeva","orcid":null},"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":"Aigerim Janaliyeva","raw_affiliation_strings":["Institute of Smart Systems and Artificial Intelligence (ISSAI), Nazarbayev University, Nur-Sultan, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Smart Systems and Artificial Intelligence (ISSAI), Nazarbayev University, Nur-Sultan, Kazakhstan","institution_ids":["https://openalex.org/I60559429"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071916620","display_name":"Almas Mirzakhmetov","orcid":"https://orcid.org/0000-0001-9264-330X"},"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":"Almas Mirzakhmetov","raw_affiliation_strings":["Institute of Smart Systems and Artificial Intelligence (ISSAI), Nazarbayev University, Nur-Sultan, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Smart Systems and Artificial Intelligence (ISSAI), Nazarbayev University, Nur-Sultan, Kazakhstan","institution_ids":["https://openalex.org/I60559429"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047310084","display_name":"Yerbolat Khassanov","orcid":"https://orcid.org/0000-0001-9422-6833"},"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":"Yerbolat Khassanov","raw_affiliation_strings":["Institute of Smart Systems and Artificial Intelligence (ISSAI), Nazarbayev University, Nur-Sultan, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Smart Systems and Artificial Intelligence (ISSAI), Nazarbayev University, Nur-Sultan, Kazakhstan","institution_ids":["https://openalex.org/I60559429"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044782949","display_name":"H\u00fcseyin Atakan Varol","orcid":"https://orcid.org/0000-0002-4042-425X"},"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":"Huseyin Atakan Varol","raw_affiliation_strings":["Institute of Smart Systems and Artificial Intelligence (ISSAI), Nazarbayev University, Nur-Sultan, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Smart Systems and Artificial Intelligence (ISSAI), Nazarbayev University, Nur-Sultan, Kazakhstan","institution_ids":["https://openalex.org/I60559429"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008567170"],"corresponding_institution_ids":["https://openalex.org/I60559429"],"apc_list":null,"apc_paid":null,"fwci":2.9384,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.92340446,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2786","last_page":"2790"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9948999881744385,"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/T11309","display_name":"Music and Audio Processing","score":0.9919000267982483,"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":0.7901845574378967},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6790487766265869},{"id":"https://openalex.org/keywords/kazakh","display_name":"Kazakh","score":0.6477240324020386},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6327655911445618},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.6304367780685425},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5725803971290588},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.513079047203064},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.484611839056015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4644795358181},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4251849353313446},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42209959030151367},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.41405200958251953},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.3288920521736145},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1738562285900116},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.1535523533821106},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10489687323570251},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07413607835769653}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7901845574378967},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6790487766265869},{"id":"https://openalex.org/C2781297163","wikidata":"https://www.wikidata.org/wiki/Q9252","display_name":"Kazakh","level":2,"score":0.6477240324020386},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6327655911445618},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.6304367780685425},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5725803971290588},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.513079047203064},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.484611839056015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4644795358181},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4251849353313446},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42209959030151367},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.41405200958251953},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.3288920521736145},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1738562285900116},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.1535523533821106},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10489687323570251},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07413607835769653},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2021-2124","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.08459","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.08459","pdf_url":"https://arxiv.org/pdf/2104.08459","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.08459","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.08459","pdf_url":"https://arxiv.org/pdf/2104.08459","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W70888257","https://openalex.org/W1522301498","https://openalex.org/W1570629387","https://openalex.org/W1749372154","https://openalex.org/W1875231349","https://openalex.org/W2152859600","https://openalex.org/W2252174795","https://openalex.org/W2519091744","https://openalex.org/W2527729766","https://openalex.org/W2591927543","https://openalex.org/W2889028433","https://openalex.org/W2901997113","https://openalex.org/W2903739847","https://openalex.org/W2945078028","https://openalex.org/W2946200149","https://openalex.org/W2952711665","https://openalex.org/W2963609956","https://openalex.org/W2963927338","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964281804","https://openalex.org/W2970730223","https://openalex.org/W2972359262","https://openalex.org/W2973034126","https://openalex.org/W3009096638","https://openalex.org/W3015338123","https://openalex.org/W3016160783","https://openalex.org/W3094002217","https://openalex.org/W3155453618"],"related_works":["https://openalex.org/W2031768607","https://openalex.org/W3164858600","https://openalex.org/W3109498233","https://openalex.org/W4200068392","https://openalex.org/W4297798732","https://openalex.org/W4205278983","https://openalex.org/W4298324454","https://openalex.org/W3161890269","https://openalex.org/W3192805203","https://openalex.org/W2152669512"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,11],"high-quality":[4],"open-source":[5],"speech":[6],"synthesis":[7],"dataset":[8,22,47,70,116],"for":[9,121,128],"Kazakh,":[10],"low-resource":[12],"language":[13],"spoken":[14,32],"by":[15,33,67],"over":[16],"13":[17],"million":[18],"people":[19],"worldwide.":[20],"The":[21,131],"consists":[23],"of":[24,28,85],"about":[25],"93":[26],"hours":[27],"transcribed":[29],"audio":[30],"recordings":[31],"two":[34],"professional":[35],"speakers":[36],"(female":[37],"and":[38,58,73,76,94,135],"male).":[39],"It":[40],"is":[41],"the":[42,69,83,98,109],"first":[43],"publicly":[44],"available":[45],"large-scale":[46],"developed":[48],"to":[49],"promote":[50],"Kazakh":[51],"text-to-speech":[52],"(TTS)":[53],"applications":[54],"in":[55],"both":[56,122],"academia":[57],"industry.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63,88],"share":[64],"our":[65,86,115],"experience":[66],"describing":[68],"development":[71],"procedures":[72],"faced":[74],"challenges,":[75],"discuss":[77],"important":[78],"future":[79],"directions.":[80],"To":[81],"demonstrate":[82],"reliability":[84],"dataset,":[87,132],"built":[89],"baseline":[90],"end-to-end":[91],"TTS":[92,111,137],"models":[93,112,138],"evaluated":[95],"them":[96,126],"using":[97],"subjective":[99],"mean":[100],"opinion":[101],"score":[102],"(MOS)":[103],"measure.":[104],"Evaluation":[105],"results":[106],"show":[107],"that":[108],"best":[110],"trained":[113],"on":[114],"achieve":[117],"MOS":[118],"above":[119],"4":[120],"speakers,":[123],"which":[124],"makes":[125],"applicable":[127],"practical":[129],"use.":[130],"training":[133],"recipe,":[134],"pretrained":[136],"are":[139],"freely":[140],"available.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}
