{"id":"https://openalex.org/W4408281718","doi":"https://doi.org/10.1109/iecon55916.2024.10905876","title":"An Open-Source Tatar Speech Commands Dataset for IoT and Robotics Applications","display_name":"An Open-Source Tatar Speech Commands Dataset for IoT and Robotics Applications","publication_year":2024,"publication_date":"2024-11-03","ids":{"openalex":"https://openalex.org/W4408281718","doi":"https://doi.org/10.1109/iecon55916.2024.10905876"},"language":"en","primary_location":{"id":"doi:10.1109/iecon55916.2024.10905876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iecon55916.2024.10905876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2024 - 50th Annual Conference of the IEEE Industrial Electronics Society","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/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"],"raw_orcid":null,"affiliations":[{"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"],"raw_orcid":null,"affiliations":[{"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/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 (Volga Region) Federal University,Kazan,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kazan (Volga Region) Federal University,Kazan,Russia","institution_ids":["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"],"raw_orcid":null,"affiliations":[{"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":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5826,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70791674,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.8985999822616577,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.8985999822616577,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8431000113487244,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.8163999915122986,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9335477352142334},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7229903936386108},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.6955164074897766},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5635079145431519},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5603907704353333},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5250535011291504},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38084712624549866},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3029196560382843},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1663593351840973},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08487933874130249}],"concepts":[{"id":"https://openalex.org/C2780124745","wikidata":"https://www.wikidata.org/wiki/Q25285","display_name":"Tatar","level":2,"score":0.9335477352142334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7229903936386108},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.6955164074897766},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5635079145431519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5603907704353333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5250535011291504},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38084712624549866},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3029196560382843},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1663593351840973},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08487933874130249},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0},{"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/iecon55916.2024.10905876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iecon55916.2024.10905876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2024 - 50th Annual Conference of the IEEE Industrial Electronics Society","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2903372879","https://openalex.org/W2936774411","https://openalex.org/W2998830286","https://openalex.org/W3100732527","https://openalex.org/W3110489441","https://openalex.org/W3196974791","https://openalex.org/W3198035615","https://openalex.org/W4200309172","https://openalex.org/W4220888499","https://openalex.org/W4223910171","https://openalex.org/W4293363567","https://openalex.org/W4385823254","https://openalex.org/W4392981865","https://openalex.org/W4392982082","https://openalex.org/W4401017743","https://openalex.org/W6750665317","https://openalex.org/W6794888937","https://openalex.org/W6803049385","https://openalex.org/W6849146053","https://openalex.org/W6853294770","https://openalex.org/W6869415701"],"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/W2489633503","https://openalex.org/W3088326158","https://openalex.org/W4380925131","https://openalex.org/W2125727558","https://openalex.org/W2146496127"],"abstract_inverted_index":{"Speech":[0,29],"command":[1],"recognition":[2],"(SCR)":[3],"is":[4,17,32],"the":[5,55,65,74,83,97,102,108,134,148,161,167],"task":[6],"of":[7,76,94,130,163],"detecting":[8],"predefined":[9],"voice":[10,21],"commands":[11,52,63],"in":[12,20,64],"an":[13,49,92,116,126],"audio":[14],"stream.":[15],"SCR":[16,40],"used":[18],"widely":[19],"assistants,":[22],"augmented":[23],"reality,":[24],"and":[25,38,68,81,112,142,152],"robotics.":[26],"Nowadays,":[27],"Google":[28],"Commands":[30],"(GSC)":[31],"a":[33],"benchmark":[34],"dataset":[35,53,60,67],"for":[36,42,54,139,166],"training":[37],"testing":[39],"models":[41,154],"English.":[43],"In":[44],"this":[45],"work,":[46],"we":[47,79],"developed":[48],"open-source":[50],"speech":[51],"low-resourced":[56],"Tatar":[57,168],"language.":[58,169],"The":[59,89,122],"employs":[61],"35":[62],"GSC":[66],"contains":[69],"3,547":[70],"utterances.":[71],"To":[72],"prove":[73],"efficacy":[75],"our":[77,87],"dataset,":[78,149],"trained":[80],"evaluated":[82],"Keyword-MLP":[84],"model":[85,90,103,124],"on":[86,96,115,133],"dataset.":[88],"achieved":[91],"accuracy":[93],"98.28%":[95],"test":[98],"set.":[99],"We":[100,145],"optimized":[101,123],"by":[104],"converting":[105],"it":[106,114,137],"to":[107,159],"ONNX":[109],"Runtime":[110],"format":[111],"deployed":[113],"NVIDIA":[117],"Jetson":[118],"Orin":[119],"NX":[120],"16GB.":[121],"showed":[125],"average":[127],"inference":[128],"time":[129],"0.003":[131],"s":[132],"device,":[135],"making":[136],"suitable":[138],"real-time":[140],"IoT":[141],"robotics":[143],"applications.":[144],"have":[146],"made":[147],"source":[150],"code,":[151],"pretrained":[153],"publicly":[155],"available":[156],"at":[157],"https://github.com/IS2AI/TatarSCR":[158],"promote":[160],"development":[162],"voice-controlled":[164],"systems":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
