{"id":"https://openalex.org/W4392981865","doi":"https://doi.org/10.1109/icaiic60209.2024.10463419","title":"Noise-Robust Multilingual Speech Recognition and the Tatar Speech Corpus","display_name":"Noise-Robust Multilingual Speech Recognition and the Tatar Speech Corpus","publication_year":2024,"publication_date":"2024-02-19","ids":{"openalex":"https://openalex.org/W4392981865","doi":"https://doi.org/10.1109/icaiic60209.2024.10463419"},"language":"en","primary_location":{"id":"doi:10.1109/icaiic60209.2024.10463419","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic60209.2024.10463419","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/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 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","Tatarstan Academy of Sciences, Institute of Applied Semiotics, 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":"Tatarstan Academy of Sciences, Institute of Applied Semiotics, 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"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Bulat Khakimov","raw_affiliation_strings":["Institute of Applied Semiotics,Tatarstan Academy of Sciences,Kazan,Russia","Tatarstan Academy of Sciences, Institute of Applied Semiotics, 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":"Tatarstan Academy of Sciences, Institute of Applied Semiotics, Kazan, Russia","institution_ids":["https://openalex.org/I4210154344"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104261542","display_name":"Mansur Galimov","orcid":null},"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":"Mansur Galimov","raw_affiliation_strings":["Institute of Applied Semiotics,Tatarstan Academy of Sciences,Kazan,Russia","Tatarstan Academy of Sciences, Institute of Applied Semiotics, 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":"Tatarstan Academy of Sciences, Institute of Applied Semiotics, Kazan, Russia","institution_ids":["https://openalex.org/I4210154344"]}]},{"author_position":"middle","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":false,"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/A5094347886","display_name":"Adal Abilbekov","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":"Adal Abilbekov","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":"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":7,"corresponding_author_ids":["https://openalex.org/A5008567170"],"corresponding_institution_ids":["https://openalex.org/I60559429"],"apc_list":null,"apc_paid":null,"fwci":14.315,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.98670556,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"732","last_page":"737"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13122","display_name":"Linguistics and Cultural Studies","score":0.9557999968528748,"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"}},"topics":[{"id":"https://openalex.org/T13122","display_name":"Linguistics and Cultural Studies","score":0.9557999968528748,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9531999826431274,"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/speech-recognition","display_name":"Speech recognition","score":0.7976861000061035},{"id":"https://openalex.org/keywords/tatar","display_name":"Tatar","score":0.7761911153793335},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7016511559486389},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5586146116256714},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.46222245693206787},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45045924186706543},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3526318669319153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32969534397125244},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32948610186576843},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19749358296394348}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7976861000061035},{"id":"https://openalex.org/C2780124745","wikidata":"https://www.wikidata.org/wiki/Q25285","display_name":"Tatar","level":2,"score":0.7761911153793335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7016511559486389},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5586146116256714},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.46222245693206787},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45045924186706543},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3526318669319153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32969534397125244},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32948610186576843},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19749358296394348},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icaiic60209.2024.10463419","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic60209.2024.10463419","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W1992912377","https://openalex.org/W2025198378","https://openalex.org/W2070707809","https://openalex.org/W2127141656","https://openalex.org/W2142416747","https://openalex.org/W2165935721","https://openalex.org/W2593116425","https://openalex.org/W2807869487","https://openalex.org/W2889669262","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2962826786","https://openalex.org/W2963122170","https://openalex.org/W2964115348","https://openalex.org/W2964309797","https://openalex.org/W2967570265","https://openalex.org/W2971758476","https://openalex.org/W2973049979","https://openalex.org/W2979826702","https://openalex.org/W3008434450","https://openalex.org/W3008480565","https://openalex.org/W3015312544","https://openalex.org/W3097777922","https://openalex.org/W3155453618","https://openalex.org/W3169369929","https://openalex.org/W3196419581","https://openalex.org/W3202648695","https://openalex.org/W4226337077","https://openalex.org/W4296068757","https://openalex.org/W4297841565","https://openalex.org/W4311000453","https://openalex.org/W4318484710","https://openalex.org/W4319862635","https://openalex.org/W4323066695","https://openalex.org/W4327927983","https://openalex.org/W4388721354","https://openalex.org/W6687566353","https://openalex.org/W6703548435","https://openalex.org/W6771467084","https://openalex.org/W6850218400"],"related_works":["https://openalex.org/W127416991","https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2036933852","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W4253660971","https://openalex.org/W2041273198"],"abstract_inverted_index":{"After":[0],"focusing":[1],"on":[2],"individual":[3],"languages":[4,44,107],"for":[5,42,46,62,73,83,96,122,132,178],"a":[6,59,74,84],"long":[7],"time,":[8],"multilingual":[9,174],"automatic":[10],"speech":[11,30,120,129,175],"recognition":[12,130,176],"has":[13],"recently":[14],"become":[15],"an":[16],"active":[17],"area":[18],"of":[19,28,37,86,108],"research.":[20,163],"For":[21],"instance,":[22],"Whisper":[23,38,65],"by":[24],"OpenAI":[25],"is":[26,39,71,148],"capable":[27],"recognizing":[29],"in":[31],"99":[32],"languages.":[33,88],"However,":[34],"the":[35,63,98,105,109,116,123,136,140,172],"performance":[36,70,82,95,131],"significantly":[40],"lower":[41],"low-resource":[43,180],"than":[45],"high-resource":[47,87],"ones.":[48],"In":[49],"this":[50,56],"work,":[51],"we":[52],"aim":[53],"to":[54,151,160],"address":[55],"and":[57,104,158],"present":[58],"fine-tuning":[60,168],"strategy":[61],"pre-trained":[64],"model":[66,92,137,147,157],"so":[67],"that":[68,128,166],"its":[69],"improved":[72],"low":[75],"-":[76],"resource":[77],"language":[78,100,181],"family":[79,101],"while":[80],"maintaining":[81],"set":[85],"Specifically,":[89],"our":[90,156,167],"Soyle":[91],"exhibited":[93],"high":[94],"both":[97],"Turkic":[99],"(11":[102],"languages)":[103],"official":[106],"United":[110],"Nations.":[111],"Our":[112,146],"work":[113],"also":[114,149],"presents":[115],"first":[117],"large":[118],"open-source":[119,155],"corpus":[121],"Tatar":[124,133,142],"language.":[125],"We":[126,154,164],"demonstrate":[127],"improves":[134],"with":[135],"trained":[138,150],"using":[139],"new":[141],"Speech":[143],"Corpus":[144],"(TatSC).":[145],"be":[152],"noise-robust.":[153],"TatSC":[159],"encourage":[161],"further":[162],"envision":[165],"approach":[169],"will":[170],"guide":[171],"creation":[173],"models":[177],"other":[179],"families.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
