{"id":"https://openalex.org/W4315786723","doi":"https://doi.org/10.3390/s23020870","title":"A Study of Speech Recognition for Kazakh Based on Unsupervised Pre-Training","display_name":"A Study of Speech Recognition for Kazakh Based on Unsupervised Pre-Training","publication_year":2023,"publication_date":"2023-01-12","ids":{"openalex":"https://openalex.org/W4315786723","doi":"https://doi.org/10.3390/s23020870","pmid":"https://pubmed.ncbi.nlm.nih.gov/36679666"},"language":"en","primary_location":{"id":"doi:10.3390/s23020870","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23020870","pdf_url":"https://www.mdpi.com/1424-8220/23/2/870/pdf?version=1673505782","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/23/2/870/pdf?version=1673505782","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042298076","display_name":"Weijing Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijing Meng","raw_affiliation_strings":["College of Information Science and Engineering, Xinjiang University, Urumqi 830017, China","Xinjiang Multilingual Information Technology Laboratory, Urumqi 830017, China"],"raw_orcid":"https://orcid.org/0000-0001-9902-5061","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Xinjiang University, Urumqi 830017, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Multilingual Information Technology Laboratory, Urumqi 830017, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076021252","display_name":"Nurmemet Yolwas","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Nurmemet Yolwas","raw_affiliation_strings":["College of Information Science and Engineering, Xinjiang University, Urumqi 830017, China","Xinjiang Multilingual Information Technology Laboratory, Urumqi 830017, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Xinjiang University, Urumqi 830017, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Multilingual Information Technology Laboratory, Urumqi 830017, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076021252"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":2.0449,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.88895988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"23","issue":"2","first_page":"870","last_page":"870"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9850000143051147,"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/T11309","display_name":"Music and Audio Processing","score":0.9825999736785889,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8009006977081299},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7634927034378052},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7427292466163635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49590715765953064},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4794275164604187},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47341638803482056},{"id":"https://openalex.org/keywords/kazakh","display_name":"Kazakh","score":0.4549126923084259},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.4461626410484314},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42157113552093506},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4196872115135193},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39512187242507935},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3548152446746826},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.10396537184715271},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07774049043655396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8009006977081299},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7634927034378052},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7427292466163635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49590715765953064},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4794275164604187},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47341638803482056},{"id":"https://openalex.org/C2781297163","wikidata":"https://www.wikidata.org/wiki/Q9252","display_name":"Kazakh","level":2,"score":0.4549126923084259},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4461626410484314},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42157113552093506},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4196872115135193},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39512187242507935},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3548152446746826},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.10396537184715271},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07774049043655396},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009622","descriptor_name":"Noise","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009622","descriptor_name":"Noise","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009622","descriptor_name":"Noise","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D049250","descriptor_name":"Speech Recognition Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D049250","descriptor_name":"Speech Recognition Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D049250","descriptor_name":"Speech Recognition Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.3390/s23020870","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23020870","pdf_url":"https://www.mdpi.com/1424-8220/23/2/870/pdf?version=1673505782","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:36679666","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36679666","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9863384","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9863384","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC9863384/pdf/sensors-23-00870.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:e26c6488acdf497b9c7f56ad714abc8c","is_oa":true,"landing_page_url":"https://doaj.org/article/e26c6488acdf497b9c7f56ad714abc8c","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 23, Iss 2, p 870 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/23/2/870/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s23020870","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Sensors; Volume 23; Issue 2; Pages: 870","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s23020870","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23020870","pdf_url":"https://www.mdpi.com/1424-8220/23/2/870/pdf?version=1673505782","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4315786723.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2124509324","https://openalex.org/W2134800885","https://openalex.org/W2729190387","https://openalex.org/W2759071281","https://openalex.org/W2799207367","https://openalex.org/W2888867175","https://openalex.org/W2892009249","https://openalex.org/W2896457183","https://openalex.org/W2926827382","https://openalex.org/W2938947737","https://openalex.org/W2940322076","https://openalex.org/W2953190524","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963308316","https://openalex.org/W2963834942","https://openalex.org/W2964243274","https://openalex.org/W2967065585","https://openalex.org/W2972389417","https://openalex.org/W2972818416","https://openalex.org/W3007328579","https://openalex.org/W3015265920","https://openalex.org/W3015338123","https://openalex.org/W3015585292","https://openalex.org/W3016160783","https://openalex.org/W3036601975","https://openalex.org/W3095351420","https://openalex.org/W3122931219","https://openalex.org/W3134970617","https://openalex.org/W3155427814","https://openalex.org/W3155453618","https://openalex.org/W3160345865","https://openalex.org/W3165924482","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6739901393","https://openalex.org/W6780218876","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2145230572","https://openalex.org/W2166312020","https://openalex.org/W3094220251","https://openalex.org/W3172030588","https://openalex.org/W4401751953","https://openalex.org/W2914064142","https://openalex.org/W156567445","https://openalex.org/W3136989387","https://openalex.org/W4287266619","https://openalex.org/W3082335021"],"abstract_inverted_index":{"Building":[0],"a":[1,8,15,59,97,213,227],"good":[2,31],"speech":[3,35,94,126,135,167,218],"recognition":[4],"system":[5],"usually":[6],"requires":[7],"lot":[9],"of":[10,100,134,185,212,216,231,252],"pairing":[11],"data,":[12],"which":[13,80,112,246],"poses":[14],"big":[16],"challenge":[17],"for":[18],"low-resource":[19,34],"languages,":[20,150],"such":[21],"as":[22],"Kazakh.":[23],"In":[24,51],"recent":[25],"years,":[26],"unsupervised":[27,85],"pre-training":[28,86,154,199,211],"has":[29,181],"achieved":[30,226],"performance":[32,133],"in":[33,42,187],"recognition,":[36],"but":[37],"it":[38],"is":[39,55,81,128,155],"rarely":[40],"used":[41,89,129],"Kazakh":[43,194,202,217],"and":[44,47,71,76,104,151],"other":[45],"Central":[46],"West":[48],"Asian":[49],"languages.":[50],"this":[52],"paper,":[53],"wav2vec2.0":[54],"improved":[56],"by":[57,208,221],"integrating":[58],"Factorized":[60],"TDNN":[61],"layer":[62],"to":[63,90,107,130,249],"better":[64,157],"preserve":[65],"the":[66,69,72,78,92,108,116,123,132,145,152,159,175,188,193,198,204,234,239,250,253,258],"relationship":[67],"between":[68],"voice":[70],"time":[73],"step":[74],"before":[75],"after":[77],"quantization,":[79],"called":[82],"wav2vec-F.":[83],"The":[84,137,162,210],"strategy":[87],"was":[88,105,113,247],"learn":[91],"potential":[93],"representation":[95],"from":[96,148],"large":[98],"number":[99],"unlabeled":[101,146],"audio":[102],"data":[103,147,163,219,241,260],"applied":[106],"cross-language":[109],"ASR":[110],"task,":[111],"optimized":[114],"using":[115,166,200],"noise":[117],"contrast":[118],"binary":[119],"classification":[120],"task.":[121],"At":[122],"same":[124],"time,":[125],"synthesis":[127,168],"promote":[131],"recognition.":[136],"experiment":[138],"shows":[139],"that":[140],"wav2vec-F":[141],"can":[142,169],"effectively":[143],"utilize":[144],"non-target":[149],"multi-language":[153,222],"obviously":[156],"than":[158],"single-language":[160],"pre-training.":[161],"enhancement":[164],"method":[165],"bring":[170],"huge":[171],"benefits.":[172],"Compared":[173],"with":[174,224],"baseline":[176],"model,":[177],"Librispeech's":[178],"test-clean":[179],"dataset":[180],"an":[182],"average":[183],"reduction":[184],"1.9%":[186],"word":[189,205,228],"error":[190,206,229],"rate.":[191],"On":[192],"KSC":[195,235],"test":[196,236],"set,":[197],"only":[201,243],"reduced":[203],"rate":[207,230],"3.8%.":[209],"small":[214],"amount":[215],"synthesized":[220],"combined":[223],"TTS":[225],"8.6%":[232],"on":[233],"set":[237],"when":[238,257],"labeled":[240,259],"were":[242,261],"10":[244],"h,":[245],"comparable":[248],"results":[251],"previous":[254],"end-to-end":[255],"model":[256],"30":[262],"times":[263],"less.":[264]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7}],"updated_date":"2026-02-03T00:53:05.648605","created_date":"2025-10-10T00:00:00"}