{"id":"https://openalex.org/W4392982082","doi":"https://doi.org/10.1109/icaiic60209.2024.10463261","title":"TatarTTS: An Open-Source Text-to-Speech Synthesis Dataset for the Tatar Language","display_name":"TatarTTS: An Open-Source Text-to-Speech Synthesis Dataset for the Tatar Language","publication_year":2024,"publication_date":"2024-02-19","ids":{"openalex":"https://openalex.org/W4392982082","doi":"https://doi.org/10.1109/icaiic60209.2024.10463261"},"language":"en","primary_location":{"id":"doi:10.1109/icaiic60209.2024.10463261","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icaiic60209.2024.10463261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","raw_type":"proceedings-article"},"type":"article","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/A5000211688","display_name":"Daniil Orel","orcid":"https://orcid.org/0009-0007-5600-7032"},"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":"Daniil Orel","raw_affiliation_strings":["Institute of Smart Systems and AI, Nazarbayev University,Astana,Kazakhstan","Institute of Smart Systems and AI, Nazarbayev University, Astana, Kazakhstan"],"affiliations":[{"raw_affiliation_string":"Institute of Smart Systems and AI, Nazarbayev University,Astana,Kazakhstan","institution_ids":["https://openalex.org/I60559429"]},{"raw_affiliation_string":"Institute of Smart Systems and AI, Nazarbayev University, Astana, Kazakhstan","institution_ids":["https://openalex.org/I60559429"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024720741","display_name":"Askat Kuzdeuov","orcid":"https://orcid.org/0000-0001-6169-8252"},"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":"Askat Kuzdeuov","raw_affiliation_strings":["Institute of Smart Systems and AI, Nazarbayev University,Astana,Kazakhstan","Institute of Smart Systems and AI, Nazarbayev University, Astana, Kazakhstan"],"affiliations":[{"raw_affiliation_string":"Institute of Smart Systems and AI, Nazarbayev University,Astana,Kazakhstan","institution_ids":["https://openalex.org/I60559429"]},{"raw_affiliation_string":"Institute of Smart Systems and AI, Nazarbayev University, Astana, Kazakhstan","institution_ids":["https://openalex.org/I60559429"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071185157","display_name":"Rinat Gilmullin","orcid":"https://orcid.org/0000-0002-8520-8921"},"institutions":[{"id":"https://openalex.org/I4210154344","display_name":"Tatarstan Academy of Sciences","ror":"https://ror.org/05b52bg33","country_code":"RU","type":"other","lineage":["https://openalex.org/I4210154344"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Rinat Gilmullin","raw_affiliation_strings":["Institute of Applied Semiotics, Tatarstan Academy of Sciences,Kazan,Russia","Institute of Applied Semiotics, Tatarstan Academy of Sciences, Kazan, Russia"],"affiliations":[{"raw_affiliation_string":"Institute of Applied Semiotics, Tatarstan Academy of Sciences,Kazan,Russia","institution_ids":["https://openalex.org/I4210154344"]},{"raw_affiliation_string":"Institute of Applied Semiotics, Tatarstan Academy of Sciences, Kazan, Russia","institution_ids":["https://openalex.org/I4210154344"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024072028","display_name":"Bulat Khakimov","orcid":"https://orcid.org/0000-0003-0126-9522"},"institutions":[{"id":"https://openalex.org/I4210154344","display_name":"Tatarstan Academy of Sciences","ror":"https://ror.org/05b52bg33","country_code":"RU","type":"other","lineage":["https://openalex.org/I4210154344"]},{"id":"https://openalex.org/I21203515","display_name":"Kazan Federal University","ror":"https://ror.org/05256ym39","country_code":"RU","type":"education","lineage":["https://openalex.org/I21203515"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Bulat Khakimov","raw_affiliation_strings":["Kazan Federal University, Institute of Applied Semiotics, Tatarstan Academy of Sciences,Kazan,Russia"],"affiliations":[{"raw_affiliation_string":"Kazan Federal University, Institute of Applied Semiotics, Tatarstan Academy of Sciences,Kazan,Russia","institution_ids":["https://openalex.org/I4210154344","https://openalex.org/I21203515"]}]},{"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 AI, Nazarbayev University,Astana,Kazakhstan","Institute of Smart Systems and AI, Nazarbayev University, Astana, Kazakhstan"],"affiliations":[{"raw_affiliation_string":"Institute of Smart Systems and AI, Nazarbayev University,Astana,Kazakhstan","institution_ids":["https://openalex.org/I60559429"]},{"raw_affiliation_string":"Institute of Smart Systems and AI, Nazarbayev University, Astana, Kazakhstan","institution_ids":["https://openalex.org/I60559429"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5000211688"],"corresponding_institution_ids":["https://openalex.org/I60559429"],"apc_list":null,"apc_paid":null,"fwci":0.3651,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61879391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"717","last_page":"721"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9775999784469604,"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":0.9775999784469604,"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":0.9509999752044678,"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/tatar","display_name":"Tatar","score":0.9301737546920776},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7787796258926392},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5714106559753418},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5064677000045776},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.485825777053833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47281137108802795},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4370183050632477},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3324568569660187},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09188419580459595},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.04633378982543945}],"concepts":[{"id":"https://openalex.org/C2780124745","wikidata":"https://www.wikidata.org/wiki/Q25285","display_name":"Tatar","level":2,"score":0.9301737546920776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7787796258926392},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5714106559753418},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5064677000045776},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.485825777053833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47281137108802795},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4370183050632477},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3324568569660187},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09188419580459595},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.04633378982543945},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icaiic60209.2024.10463261","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icaiic60209.2024.10463261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1598857024","https://openalex.org/W2525778437","https://openalex.org/W2531638282","https://openalex.org/W2591927543","https://openalex.org/W2928069500","https://openalex.org/W2972359262","https://openalex.org/W3009431628","https://openalex.org/W3127803403","https://openalex.org/W3151309757","https://openalex.org/W3174758275","https://openalex.org/W4205455244","https://openalex.org/W4224247062","https://openalex.org/W4285077564","https://openalex.org/W4288100462","https://openalex.org/W4296068757","https://openalex.org/W4385764125","https://openalex.org/W4385823191","https://openalex.org/W4385823254","https://openalex.org/W6731944675","https://openalex.org/W6796464841","https://openalex.org/W6804012711","https://openalex.org/W6849146053"],"related_works":["https://openalex.org/W4200210547","https://openalex.org/W2591869249","https://openalex.org/W3123570765","https://openalex.org/W3122923603","https://openalex.org/W3162919690","https://openalex.org/W3088326158","https://openalex.org/W2489633503","https://openalex.org/W4380925131","https://openalex.org/W2125727558","https://openalex.org/W127416991"],"abstract_inverted_index":{"This":[0],"paper":[1,60],"introduces":[2],"an":[3],"open-source":[4],"dataset":[5,14,38],"for":[6,64],"speech":[7],"synthesis":[8],"in":[9,53],"the":[10,35,62,66,69,79,82,93],"Tatar":[11,49],"language.":[12],"The":[13,59,100],"comprises":[15],"approximately":[16],"70":[17],"hours":[18],"of":[19,39,81],"transcribed":[20],"audio":[21],"recordings,":[22],"featuring":[23],"two":[24],"professional":[25],"speakers":[26],"(one":[27],"male":[28],"and":[29,56,72,90,104],"one":[30],"female).":[31],"Notably,":[32],"it":[33],"is":[34,43],"first":[36],"large-scale":[37],"its":[40],"kind":[41],"that":[42],"publicly":[44,109],"available,":[45],"aimed":[46],"at":[47],"promoting":[48],"text-to-speech":[50],"(TTS)":[51],"applications":[52],"both":[54],"academic":[55],"industrial":[57],"contexts.":[58],"describes":[61],"procedures":[63],"developing":[65],"dataset,":[67,83,101],"discusses":[68],"challenges":[70],"faced,":[71],"outlines":[73],"important":[74],"future":[75],"directions.":[76],"To":[77],"demonstrate":[78],"reliability":[80],"baseline":[84],"end-to-end":[85],"TTS":[86,106],"models":[87,107],"were":[88],"built":[89],"evaluated":[91],"using":[92],"subjective":[94],"mean":[95],"opinion":[96],"score":[97],"(MOS)":[98],"measure.":[99],"training":[102],"recipe,":[103],"pretrained":[105],"are":[108],"available.":[110]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}
