{"id":"https://openalex.org/W4385823254","doi":"https://doi.org/10.21437/interspeech.2023-249","title":"Multilingual Text-to-Speech Synthesis for Turkic Languages Using Transliteration","display_name":"Multilingual Text-to-Speech Synthesis for Turkic Languages Using Transliteration","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823254","doi":"https://doi.org/10.21437/interspeech.2023-249"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-249","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://nur.nu.edu.kz/bitstreams/41ebd349-6d56-4439-9ad5-b8d21a2d193d/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075840040","display_name":"Rustem Yeshpanov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rustem Yeshpanov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","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":"last","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":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2785,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.82375682,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5521","last_page":"5525"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9812999963760376,"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":0.9812999963760376,"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":0.9807999730110168,"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/T13122","display_name":"Linguistics and Cultural Studies","score":0.9431999921798706,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transliteration","display_name":"Transliteration","score":0.8891775608062744},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7531891465187073},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6455966234207153},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5934569239616394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5761160850524902},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44506263732910156}],"concepts":[{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.8891775608062744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7531891465187073},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6455966234207153},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5934569239616394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5761160850524902},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44506263732910156}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-249","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:nur.nu.edu.kz:123456789/9886","is_oa":true,"landing_page_url":"https://nur.nu.edu.kz/handle/123456789/9886","pdf_url":"https://nur.nu.edu.kz/bitstreams/41ebd349-6d56-4439-9ad5-b8d21a2d193d/download","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"INTERSPEECH 2023, (2023)","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:nur.nu.edu.kz:123456789/9886","is_oa":true,"landing_page_url":"https://nur.nu.edu.kz/handle/123456789/9886","pdf_url":"https://nur.nu.edu.kz/bitstreams/41ebd349-6d56-4439-9ad5-b8d21a2d193d/download","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"INTERSPEECH 2023, (2023)","raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385823254.pdf","grobid_xml":"https://content.openalex.org/works/W4385823254.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2069051384","https://openalex.org/W2402792586","https://openalex.org/W2003588142","https://openalex.org/W2069398544","https://openalex.org/W1773556797","https://openalex.org/W3155028086","https://openalex.org/W2900394151","https://openalex.org/W2154827307","https://openalex.org/W2554259713","https://openalex.org/W1974301530"],"abstract_inverted_index":{"This":[0],"work":[1],"aims":[2],"to":[3,47,105],"build":[4],"a":[5,35],"multilingual":[6,122],"text-to-speech":[7],"(TTS)":[8],"synthesis":[9],"system":[10,57],"for":[11,50,78],"ten":[12],"lower-resourced":[13],"Turkic":[14,81,90,123],"languages:":[15],"Azerbaijani,":[16],"Bashkir,":[17],"Kazakh,":[18],"Kyrgyz,":[19],"Sakha,":[20],"Tatar,":[21],"Turkish,":[22],"Turkmen,":[23],"Uyghur,":[24],"and":[25,127,141],"Uzbek.":[26],"We":[27],"specifically":[28],"target":[29],"the":[30,40,60,68,72,79,86,89,93,96,106,113,116,121,135],"zero-shot":[31],"learning":[32],"scenario,":[33],"where":[34],"TTS":[36,56,124],"model":[37,125],"trained":[38,65],"using":[39,66],"data":[41,70],"of":[42,71,88,95,115,134],"one":[43],"language":[44],"is":[45],"applied":[46],"synthesise":[48],"speech":[49,77],"other,":[51],"unseen":[52],"languages.":[53],"An":[54],"end-to-end":[55],"based":[58],"on":[59],"Tacotron":[61],"2":[62],"architecture":[63],"was":[64],"only":[67],"available":[69,144],"Kazakh":[73,107],"language.":[74],"To":[75,110,131],"generate":[76],"other":[80],"languages,":[82],"we":[83,119,137],"first":[84],"mapped":[85],"letters":[87],"alphabets":[91],"onto":[92],"symbols":[94],"International":[97],"Phonetic":[98],"Alphabet":[99],"(IPA),":[100],"which":[101],"were":[102],"then":[103],"converted":[104],"alphabet":[108],"letters.":[109],"demon":[111],"strate":[112],"feasibility":[114],"proposed":[117],"approach,":[118],"evaluated":[120],"subjectively":[126],"obtained":[128],"promising":[129],"results.":[130],"enable":[132],"replication":[133],"experiments,":[136],"make":[138],"our":[139,146],"code":[140],"dataset":[142],"publicly":[143],"in":[145],"GitHub":[147],"repository.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-09T07:27:16.801131","created_date":"2025-10-10T00:00:00"}
