{"id":"https://openalex.org/W7124737216","doi":"https://doi.org/10.25587/3034-7378-2025-4-56-78","title":"Transformer-Based Neural Network Approaches for Speech Recognition and Synthesis in the Sakha Language","display_name":"Transformer-Based Neural Network Approaches for Speech Recognition and Synthesis in the Sakha Language","publication_year":2026,"publication_date":"2026-01-17","ids":{"openalex":"https://openalex.org/W7124737216","doi":"https://doi.org/10.25587/3034-7378-2025-4-56-78"},"language":"en","primary_location":{"id":"doi:10.25587/3034-7378-2025-4-56-78","doi":"https://doi.org/10.25587/3034-7378-2025-4-56-78","is_oa":true,"landing_page_url":"https://doi.org/10.25587/3034-7378-2025-4-56-78","pdf_url":"https://www.arcticjournal.ru/jour/article/download/242/190","source":{"id":"https://openalex.org/S5407055903","display_name":"Arctic XXI century","issn_l":"3034-7378","issn":["3034-7378","3034-7386"],"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":"Arctic XXI century","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://www.arcticjournal.ru/jour/article/download/242/190","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122641610","display_name":"S. P. Stepanov","orcid":"https://orcid.org/0000-0001-9445-2726","observed_orcids":["https://orcid.org/0000-0001-9445-2726"]},"institutions":[{"id":"https://openalex.org/I131550537","display_name":"North-Eastern Federal University","ror":"https://ror.org/02p6aa271","country_code":"RU","type":"education","lineage":["https://openalex.org/I131550537"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"S. P. Stepanov","raw_affiliation_strings":["M.K. Ammosov  North-Eastern  Federal University"],"raw_orcid":"https://orcid.org/0000-0001-9445-2726","affiliations":[{"raw_affiliation_string":"M.K. Ammosov  North-Eastern  Federal University","institution_ids":["https://openalex.org/I131550537"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056103860","display_name":"Dong Zhang","orcid":"https://orcid.org/0000-0003-4688-7762","observed_orcids":["https://orcid.org/0000-0003-4688-7762"]},"institutions":[{"id":"https://openalex.org/I202126657","display_name":"Qufu Normal University","ror":"https://ror.org/03ceheh96","country_code":"CN","type":"education","lineage":["https://openalex.org/I202126657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Zhang","raw_affiliation_strings":["Qufu  Normal  University"],"raw_orcid":"https://orcid.org/0000-0003-4688-7762","affiliations":[{"raw_affiliation_string":"Qufu  Normal  University","institution_ids":["https://openalex.org/I202126657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123294658","display_name":"A. A. Alekseeva","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I131550537","display_name":"North-Eastern Federal University","ror":"https://ror.org/02p6aa271","country_code":"RU","type":"education","lineage":["https://openalex.org/I131550537"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"A. A. Alekseeva","raw_affiliation_strings":["M.K.  Ammosov  North-Eastern  Federal  University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"M.K.  Ammosov  North-Eastern  Federal  University","institution_ids":["https://openalex.org/I131550537"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123311551","display_name":"V. L. Aprosimov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I131550537","display_name":"North-Eastern Federal University","ror":"https://ror.org/02p6aa271","country_code":"RU","type":"education","lineage":["https://openalex.org/I131550537"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"V. L. Aprosimov","raw_affiliation_strings":["M.K.  Ammosov  North-Eastern  Federal  University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"M.K.  Ammosov  North-Eastern  Federal  University","institution_ids":["https://openalex.org/I131550537"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123350651","display_name":"Dj. A. Fedorov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I131550537","display_name":"North-Eastern Federal University","ror":"https://ror.org/02p6aa271","country_code":"RU","type":"education","lineage":["https://openalex.org/I131550537"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dj. A. Fedorov","raw_affiliation_strings":["M.K.  Ammosov  North-Eastern  Federal  University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"M.K.  Ammosov  North-Eastern  Federal  University","institution_ids":["https://openalex.org/I131550537"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123310546","display_name":"V. S. Leveryev","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I131550537","display_name":"North-Eastern Federal University","ror":"https://ror.org/02p6aa271","country_code":"RU","type":"education","lineage":["https://openalex.org/I131550537"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"V. S. Leveryev","raw_affiliation_strings":["M.K.  Ammosov  North-Eastern  Federal  University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"M.K.  Ammosov  North-Eastern  Federal  University","institution_ids":["https://openalex.org/I131550537"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123292576","display_name":"T. A. Novgorodov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I131550537","display_name":"North-Eastern Federal University","ror":"https://ror.org/02p6aa271","country_code":"RU","type":"education","lineage":["https://openalex.org/I131550537"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"T. A. Novgorodov","raw_affiliation_strings":["M.K.  Ammosov  North-Eastern  Federal  University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"M.K.  Ammosov  North-Eastern  Federal  University","institution_ids":["https://openalex.org/I131550537"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123307626","display_name":"E. S. Podorozhnaya","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I131550537","display_name":"North-Eastern Federal University","ror":"https://ror.org/02p6aa271","country_code":"RU","type":"education","lineage":["https://openalex.org/I131550537"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"E. S. Podorozhnaya","raw_affiliation_strings":["M.K.  Ammosov  North-Eastern  Federal  University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"M.K.  Ammosov  North-Eastern  Federal  University","institution_ids":["https://openalex.org/I131550537"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123319742","display_name":"T. Z. Zakharov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I131550537","display_name":"North-Eastern Federal University","ror":"https://ror.org/02p6aa271","country_code":"RU","type":"education","lineage":["https://openalex.org/I131550537"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"T. Z. Zakharov","raw_affiliation_strings":["M.K.  Ammosov  North-Eastern  Federal  University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"M.K.  Ammosov  North-Eastern  Federal  University","institution_ids":["https://openalex.org/I131550537"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3951,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80881696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":"4","first_page":"56","last_page":"78"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.0,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.0,"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/yakut-language","display_name":"Yakut language","score":0.996999979019165},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.7990000247955322},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.953000009059906},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.7039999961853027},{"id":"https://openalex.org/keywords/whisper","display_name":"Whisper","score":0.7699999809265137},{"id":"https://openalex.org/keywords/agglutinative-morphology","display_name":"agglutinative morphology","score":0.9259999990463257},{"id":"https://openalex.org/keywords/vowel-harmony","display_name":"vowel harmony","score":1.0},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.75},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.6980000138282776},{"id":"https://openalex.org/keywords/telegram-bot","display_name":"Telegram bot","score":0.527999997138977},{"id":"https://openalex.org/keywords/digital-accessibility","display_name":"digital accessibility","score":0.5379999876022339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7990999817848206},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5048999786376953},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5044999718666077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4925000071525574},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4875999987125397},{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.44749999046325684},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41350001096725464},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3540000021457672},{"id":"https://openalex.org/C4768521","wikidata":"https://www.wikidata.org/wiki/Q512366","display_name":"Phonotactics","level":3,"score":0.3508000075817108},{"id":"https://openalex.org/C64249296","wikidata":"https://www.wikidata.org/wiki/Q5250411","display_name":"Deep linguistic processing","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C2781280609","wikidata":"https://www.wikidata.org/wiki/Q147137","display_name":"Vowel harmony","level":3,"score":0.34689998626708984},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.33379998803138733},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.25920000672340393}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.25587/3034-7378-2025-4-56-78","doi":"https://doi.org/10.25587/3034-7378-2025-4-56-78","is_oa":true,"landing_page_url":"https://doi.org/10.25587/3034-7378-2025-4-56-78","pdf_url":"https://www.arcticjournal.ru/jour/article/download/242/190","source":{"id":"https://openalex.org/S5407055903","display_name":"Arctic XXI century","issn_l":"3034-7378","issn":["3034-7378","3034-7386"],"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":"Arctic XXI century","raw_type":"journal-article"},{"id":"pmh:https://cyberleninka.ru/article/n/transformer-based-neural-network-approaches-for-speech-recognition-and-synthesis-in-the-sakha-language","doi":null,"is_oa":true,"landing_page_url":"https://cyberleninka.ru/article/n/transformer-based-neural-network-approaches-for-speech-recognition-and-synthesis-in-the-sakha-language","pdf_url":"https://cyberleninka.ru/article/n/transformer-based-neural-network-approaches-for-speech-recognition-and-synthesis-in-the-sakha-language/pdf","source":{"id":"https://openalex.org/S4306401404","display_name":"CyberLeninK (CyberLeninka)","issn_l":null,"issn":null,"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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.25587/3034-7378-2025-4-56-78","doi":"https://doi.org/10.25587/3034-7378-2025-4-56-78","is_oa":true,"landing_page_url":"https://doi.org/10.25587/3034-7378-2025-4-56-78","pdf_url":"https://www.arcticjournal.ru/jour/article/download/242/190","source":{"id":"https://openalex.org/S5407055903","display_name":"Arctic XXI century","issn_l":"3034-7378","issn":["3034-7378","3034-7386"],"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":"Arctic XXI century","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4943999946117401,"id":"https://metadata.un.org/sdg/9"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G2517348437","display_name":null,"funder_award_id":"22.05.2025","funder_id":"https://openalex.org/F4320324099","funder_display_name":"Russian Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320324099","display_name":"Russian Science Foundation","ror":"https://ror.org/03y2gwe85"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7124737216.pdf","grobid_xml":"https://content.openalex.org/works/W7124737216.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W28412257","https://openalex.org/W1494198834","https://openalex.org/W1536721795","https://openalex.org/W2091746061","https://openalex.org/W2125838338","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2626778328","https://openalex.org/W2885185669","https://openalex.org/W2914369697","https://openalex.org/W2936774411","https://openalex.org/W2964243274","https://openalex.org/W2970971581","https://openalex.org/W2979826702","https://openalex.org/W2995929068","https://openalex.org/W3017311573","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3036601975","https://openalex.org/W3037057938","https://openalex.org/W3098403858","https://openalex.org/W3169905056","https://openalex.org/W4311000453","https://openalex.org/W4313415426","https://openalex.org/W4318484710","https://openalex.org/W4385823254","https://openalex.org/W4402112533","https://openalex.org/W4415052592"],"related_works":["https://openalex.org/W4415052592","https://openalex.org/W4320509669","https://openalex.org/W7217594420","https://openalex.org/W7106250903","https://openalex.org/W2982336461","https://openalex.org/W4416798855","https://openalex.org/W2588697303","https://openalex.org/W3167116800","https://openalex.org/W6976824662","https://openalex.org/W7133483226"],"abstract_inverted_index":{"Recent":[0],"breakthroughs":[1],"in":[2,91],"artificial":[3],"intelligence":[4],"and":[5,22,64,78,105,125,141,207],"deep":[6],"learning":[7,235],"have":[8,26],"fundamentally":[9],"transformed":[10],"the":[11,42,46,65,76,172],"landscape":[12],"of":[13,45,67,80,98,158,169,201],"spoken":[14],"language":[15,48,184],"processing":[16,70],"technologies.":[17],"Automatic":[18],"speech":[19,69,88,242],"recognition":[20,162,219],"(ASR)":[21],"text-to-speech":[23],"(TTS)":[24],"synthesis":[25,188],"emerged":[27],"as":[28,237],"essential":[29],"components":[30],"driving":[31],"digital":[32,59],"accessibility":[33],"across":[34],"diverse":[35],"linguistic":[36,124,247],"communities.":[37,248],"The":[38,186],"Sakha":[39],"language,":[40],"representing":[41],"northeastern":[43],"branch":[44],"Turkic":[47],"family,":[49],"continues":[50],"to":[51,129],"face":[52],"substantial":[53],"technological":[54],"barriers":[55],"stemming":[56],"from":[57,148],"insufficient":[58],"resources,":[60],"limited":[61],"annotated":[62],"corpora,":[63],"absence":[66],"production-ready":[68],"systems.":[71],"This":[72],"comprehensive":[73,156],"investigation":[74],"examines":[75],"feasibility":[77],"effectiveness":[79],"adapting":[81],"contemporary":[82],"transformer-based":[83],"neural":[84,187],"architectures":[85,220],"for":[86,108,115,240],"bidirectional":[87],"conversion":[89],"tasks":[90],"Sakha.":[92],"Our":[93],"research":[94],"encompasses":[95],"detailed":[96],"analysis":[97],"encoder-decoder":[99],"frameworks,":[100],"specifically":[101],"OpenAI\u2019s":[102],"Whisper":[103],"large-v3":[104],"Meta\u2019s":[106],"Wav2Vec2-BERT":[107,174],"voice-to-text":[109],"transformation,":[110],"alongside":[111],"Coqui\u2019s":[112],"XTTS-v2":[113],"system":[114,189],"text-to-voice":[116],"generation.":[117],"Particular":[118],"emphasis":[119],"is":[120],"placed":[121],"on":[122],"addressing":[123],"technical":[126],"obstacles":[127],"inherent":[128],"Sakha,":[130],"including":[131],"its":[132],"complex":[133],"agglutinative":[134],"morphological":[135],"structure,":[136],"systematic":[137],"vowel":[138],"harmony":[139],"patterns,":[140],"distinctive":[142],"phonemic":[143],"inventory":[144],"featuring":[145],"sounds":[146],"absent":[147],"most":[149],"Indo-European":[150],"languages.":[151],"Experimental":[152],"evaluation":[153],"demonstrates":[154],"that":[155],"fine-tuning":[157],"Whisper-large-v3":[159],"achieves":[160,221],"exceptional":[161],"accuracy":[163],"with":[164,181],"word":[165],"error":[166],"rate":[167],"(WER)":[168],"8%,":[170],"while":[171],"self-supervised":[173],"architecture":[175],"attains":[176],"13%":[177],"WER":[178],"when":[179],"augmented":[180],"statistical":[182],"n-gram":[183],"modeling.":[185],"exhibits":[190],"robust":[191],"performance":[192],"despite":[193],"minimal":[194],"training":[195,205],"data":[196],"availability,":[197],"achieving":[198],"average":[199],"loss":[200],"2.49":[202],"following":[203],"extended":[204],"optimization":[206],"practical":[208],"deployment":[209],"via":[210],"Telegram":[211],"messaging":[212],"bot.":[213],"Additionally,":[214],"ensemble":[215],"meta-stacking":[216],"combining":[217],"both":[218],"27%":[222],"WER,":[223],"demonstrating":[224],"effective":[225],"complementarity":[226],"through":[227],"learned":[228],"hypothesis":[229],"arbitration.":[230],"These":[231],"findings":[232],"validate":[233],"transfer":[234],"methodologies":[236],"viable":[238],"pathways":[239],"developing":[241],"technologies":[243],"serving":[244],"digitally":[245],"underrepresented":[246]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-01-20T00:00:00"}