{"id":"https://openalex.org/W7214727752","doi":"https://doi.org/10.47533/2026.1606-146x.3-08","title":"Comparative analysis of noise robustness of CNN-GRU and CNN-BiGRU models for voice activity detection in Kazakh speech","display_name":"Comparative analysis of noise robustness of CNN-GRU and CNN-BiGRU models for voice activity detection in Kazakh speech","publication_year":2026,"publication_date":"2026-09-15","ids":{"openalex":"https://openalex.org/W7214727752","doi":"https://doi.org/10.47533/2026.1606-146x.3-08"},"language":"en","primary_location":{"id":"doi:10.47533/2026.1606-146x.3-08","doi":"https://doi.org/10.47533/2026.1606-146x.3-08","is_oa":true,"landing_page_url":"https://doi.org/10.47533/2026.1606-146x.3-08","pdf_url":"https://doi.org/10.47533/2026.1606-146x.3-08","source":{"id":"https://openalex.org/S4210198950","display_name":"Bulletin of the National Engineering Academy of the Republic of Kazakhstan","issn_l":"2709-4693","issn":["2709-4693","2709-4707"],"is_oa":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bulletin of the National Engineering Academy of the Republic of Kazakhstan","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.47533/2026.1606-146x.3-08","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021005486","display_name":"Aigul Kulakayeva","orcid":"https://orcid.org/0000-0002-0143-085X","observed_orcids":["https://orcid.org/0000-0002-0143-085X"]},"institutions":[{"id":"https://openalex.org/I4210143508","display_name":"International Information Technologies University","ror":"https://ror.org/042dtza69","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4210143508"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"A. Ye. Kulakayeva","raw_affiliation_strings":["JSC \u201cInternational Information Technology University\u00bb"],"raw_orcid":"https://orcid.org/0000-0002-0143-085X","affiliations":[{"raw_affiliation_string":"JSC \u201cInternational Information Technology University\u00bb","institution_ids":["https://openalex.org/I4210143508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083030750","display_name":"Aigul Nurlankyzy","orcid":"https://orcid.org/0000-0002-0791-8573","observed_orcids":["https://orcid.org/0000-0002-0791-8573"]},"institutions":[{"id":"https://openalex.org/I204275683","display_name":"Satbayev University","ror":"https://ror.org/020cpsb96","country_code":"KZ","type":"education","lineage":["https://openalex.org/I204275683"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"A. Nurlankyzy","raw_affiliation_strings":["JSC \u201cInternational Information Technology University\u00bb,   NJSC \u201cKazakh National Research Technical University named after K.I. Satpayev\u201d"],"raw_orcid":"https://orcid.org/0000-0002-0791-8573","affiliations":[{"raw_affiliation_string":"JSC \u201cInternational Information Technology University\u00bb,   NJSC \u201cKazakh National Research Technical University named after K.I. Satpayev\u201d","institution_ids":["https://openalex.org/I204275683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031598623","display_name":"Yevgeniya A. Daineko","orcid":"https://orcid.org/0000-0001-6581-2622","observed_orcids":["https://orcid.org/0000-0001-6581-2622"]},"institutions":[{"id":"https://openalex.org/I204275683","display_name":"Satbayev University","ror":"https://ror.org/020cpsb96","country_code":"KZ","type":"education","lineage":["https://openalex.org/I204275683"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"A. Ye. Daineko","raw_affiliation_strings":["NJSC \u201cKazakh National Research Technical University named after K.I. Satpayev\u201d"],"raw_orcid":"https://orcid.org/0000-0001-6581-2622","affiliations":[{"raw_affiliation_string":"NJSC \u201cKazakh National Research Technical University named after K.I. Satpayev\u201d","institution_ids":["https://openalex.org/I204275683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016078821","display_name":"Askhat Batyrgaliyev","orcid":"https://orcid.org/0000-0002-1103-8659","observed_orcids":["https://orcid.org/0000-0002-1103-8659"]},"institutions":[{"id":"https://openalex.org/I204275683","display_name":"Satbayev University","ror":"https://ror.org/020cpsb96","country_code":"KZ","type":"education","lineage":["https://openalex.org/I204275683"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"A. Batyrgaliev","raw_affiliation_strings":["NJSC \u201cKazakh National Research Technical University named after K.I. Satpayev\u201d"],"raw_orcid":"https://orcid.org/0000-0002-1103-8659","affiliations":[{"raw_affiliation_string":"NJSC \u201cKazakh National Research Technical University named after K.I. Satpayev\u201d","institution_ids":["https://openalex.org/I204275683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"101","issue":"3","first_page":"94","last_page":"105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6133000254631042,"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":0.6133000254631042,"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":0.38530001044273376,"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/T11309","display_name":"Music and Audio Processing","score":0.00039999998989515007,"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/voice-activity-detection","display_name":"voice activity detection","score":0.9980000257492065},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.8999999761581421},{"id":"https://openalex.org/keywords/cnn-gru","display_name":"CNN-GRU","score":0.9660000205039978},{"id":"https://openalex.org/keywords/cnn-bigru","display_name":"CNN-BiGRU","score":0.9919999837875366},{"id":"https://openalex.org/keywords/bidirectional-gru","display_name":"bidirectional GRU","score":0.9850000143051147},{"id":"https://openalex.org/keywords/acoustic-noise","display_name":"acoustic noise","score":0.5540000200271606},{"id":"https://openalex.org/keywords/low-signal-to-noise-ratio","display_name":"low signal-to-noise ratio","score":0.8569999933242798},{"id":"https://openalex.org/keywords/lightweight-neural-networks","display_name":"lightweight neural networks","score":0.6629999876022339},{"id":"https://openalex.org/keywords/mobile-application","display_name":"mobile application","score":0.6050000190734863},{"id":"https://openalex.org/keywords/mel-frequency-cepstral-coefficients","display_name":"Mel-frequency cepstral coefficients","score":0.8579999804496765}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.795799970626831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7540000081062317},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7407000064849854},{"id":"https://openalex.org/C2781297163","wikidata":"https://www.wikidata.org/wiki/Q9252","display_name":"Kazakh","level":2,"score":0.6043999791145325},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5320000052452087},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5008999705314636},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4634000062942505},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45260000228881836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.448199987411499},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.4413999915122986},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.41909998655319214},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41589999198913574},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3093999922275543},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.30799999833106995},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.28369998931884766},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.47533/2026.1606-146x.3-08","doi":"https://doi.org/10.47533/2026.1606-146x.3-08","is_oa":true,"landing_page_url":"https://doi.org/10.47533/2026.1606-146x.3-08","pdf_url":"https://doi.org/10.47533/2026.1606-146x.3-08","source":{"id":"https://openalex.org/S4210198950","display_name":"Bulletin of the National Engineering Academy of the Republic of Kazakhstan","issn_l":"2709-4693","issn":["2709-4693","2709-4707"],"is_oa":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bulletin of the National Engineering Academy of the Republic of Kazakhstan","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.47533/2026.1606-146x.3-08","doi":"https://doi.org/10.47533/2026.1606-146x.3-08","is_oa":true,"landing_page_url":"https://doi.org/10.47533/2026.1606-146x.3-08","pdf_url":"https://doi.org/10.47533/2026.1606-146x.3-08","source":{"id":"https://openalex.org/S4210198950","display_name":"Bulletin of the National Engineering Academy of the Republic of Kazakhstan","issn_l":"2709-4693","issn":["2709-4693","2709-4707"],"is_oa":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bulletin of the National Engineering Academy of the Republic of Kazakhstan","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214727752.pdf","grobid_xml":"https://content.openalex.org/works/W7214727752.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2945013390","https://openalex.org/W4210381452","https://openalex.org/W4221155601","https://openalex.org/W4408150700"],"related_works":["https://openalex.org/W4417147295","https://openalex.org/W3135241621","https://openalex.org/W4386687786","https://openalex.org/W4413559249","https://openalex.org/W7117145941","https://openalex.org/W4393658134","https://openalex.org/W3090014957","https://openalex.org/W2903422430","https://openalex.org/W4410765447","https://openalex.org/W7118719565"],"abstract_inverted_index":{"This":[0],"study":[1,181],"addresses":[2],"the":[3,8,20,66,69,148,152,206],"actual":[4],"problem":[5],"of":[6,11,19,28,43,62,68,93],"improving":[7],"noise":[9,139],"robustness":[10],"voice":[12],"activity":[13],"detection":[14],"(VAD)":[15],"systems.":[16],"The":[17,47,101,180],"aim":[18],"work":[21],"is":[22,209],"to":[23,37,125,135,164,216],"conduct":[24],"a":[25,54,59,90,107,118,165],"comparative":[26],"analysis":[27],"hybrid":[29],"neural":[30],"network":[31],"architectures,":[32],"namely":[33],"CNN-GRU":[34],"and":[35,106,197],"CNN-BiGRU,":[36],"evaluate":[38],"their":[39],"effectiveness":[40],"under":[41,137,142],"conditions":[42],"intensive":[44],"acoustic":[45],"noise.":[46],"experimental":[48],"dataset":[49],"was":[50,161,202],"formed":[51],"based":[52],"on":[53,172],"Kazakh":[55],"speech":[56,191],"corpus":[57],"with":[58,89],"total":[60],"duration":[61],"332":[63],"hours.":[64],"In":[65],"course":[67],"study,":[70],"more":[71,187,210],"than":[72],"2.4":[73],"million":[74],"training":[75,176],"segments":[76],"were":[77,96,113],"prepared":[78],"from":[79,123],"30":[80,126],"speakers,":[81],"ensuring":[82],"speaker":[83],"independence.":[84],"Mel-frequency":[85],"cepstral":[86],"coefficients":[87],"(MFCCs)":[88],"temporal":[91,199],"window":[92],"120":[94],"ms":[95],"used":[97],"as":[98],"input":[99],"features.":[100],"architectures":[102],"CNN+BiGRU":[103],"(11,106":[104],"parameters)":[105,112],"lightweight":[108],"CNN+GRU":[109,207],"model":[110,154,208],"(6,050":[111],"compared.":[114],"Experimental":[115],"results":[116],"across":[117],"signal-to-noise":[119],"ratio":[120],"(SNR)":[121],"range":[122],"\u221210":[124],"dB":[127],"demonstrated":[128],"high":[129],"accuracy":[130,169],"for":[131,212],"both":[132,195],"models":[133],"(up":[134],"99%)":[136],"moderate":[138],"conditions.":[140],"However,":[141],"extremely":[143],"low":[144],"SNR":[145],"(\u221210":[146],"dB),":[147],"BiGRU":[149],"architecture":[150],"outperformed":[151],"GRU":[153],"by":[155,193],"5\u20138%.":[156],"A":[157],"\u201cspectral":[158],"specialization\u201d":[159],"effect":[160],"observed,":[162],"leading":[163],"noticeable":[166],"decrease":[167],"in":[168,177,189],"when":[170],"testing":[171],"clean":[173],"signals":[174],"after":[175],"noisy":[178],"environments.":[179],"confirms":[182],"that":[183,205],"bidirectional":[184],"layers":[185],"are":[186],"effective":[188],"reconstructing":[190],"information":[192],"analyzing":[194],"forward":[196],"backward":[198],"sequences.":[200],"It":[201],"also":[203],"established":[204],"suitable":[211],"mobile":[213],"applications":[214],"due":[215],"its":[217],"significantly":[218],"lower":[219],"computational":[220],"requirements.":[221]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-09-30T00:00:00"}