{"id":"https://openalex.org/W4401958920","doi":"https://doi.org/10.3103/s0146411624700561","title":"Building a Production-Ready Keyword Detection System on a Real-World Audio","display_name":"Building a Production-Ready Keyword Detection System on a Real-World Audio","publication_year":2024,"publication_date":"2024-08-01","ids":{"openalex":"https://openalex.org/W4401958920","doi":"https://doi.org/10.3103/s0146411624700561"},"language":"en","primary_location":{"id":"doi:10.3103/s0146411624700561","is_oa":false,"landing_page_url":"http://dx.doi.org/10.3103/s0146411624700561","pdf_url":null,"source":{"id":"https://openalex.org/S17203304","display_name":"Automatic Control and Computer Sciences","issn_l":"0146-4116","issn":["0146-4116","1558-108X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320267","host_organization_name":"Pleiades Publishing","host_organization_lineage":["https://openalex.org/P4310320267","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Pleiades Publishing","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Automatic Control and Computer Sciences","raw_type":"journal-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/A5106780832","display_name":"Eugene Zhmakin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110898","display_name":"Moscow Technical University of Communication and Informatics","ror":"https://ror.org/015zw2f19","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210110898"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Eugene Zhmakin","raw_affiliation_strings":["Moscow Technical University of Communications and Informatics (MTUCI), 111024, Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"Moscow Technical University of Communications and Informatics (MTUCI), 111024, Moscow, Russia","institution_ids":["https://openalex.org/I4210110898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084139711","display_name":"\u0413 \u041c \u041c\u043a\u0440\u0442\u0447\u044f\u043d","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110898","display_name":"Moscow Technical University of Communication and Informatics","ror":"https://ror.org/015zw2f19","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210110898"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Grach Mkrtchian","raw_affiliation_strings":["Moscow Technical University of Communications and Informatics (MTUCI), 111024, Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"Moscow Technical University of Communications and Informatics (MTUCI), 111024, Moscow, Russia","institution_ids":["https://openalex.org/I4210110898"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5106780832"],"corresponding_institution_ids":["https://openalex.org/I4210110898"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15114038,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"58","issue":"4","first_page":"454","last_page":"458"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9987000226974487,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.9029964208602905},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.5756494998931885},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.47911858558654785}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9029964208602905},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.5756494998931885},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.47911858558654785},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3103/s0146411624700561","is_oa":false,"landing_page_url":"http://dx.doi.org/10.3103/s0146411624700561","pdf_url":null,"source":{"id":"https://openalex.org/S17203304","display_name":"Automatic Control and Computer Sciences","issn_l":"0146-4116","issn":["0146-4116","1558-108X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320267","host_organization_name":"Pleiades Publishing","host_organization_lineage":["https://openalex.org/P4310320267","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Pleiades Publishing","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Automatic Control and Computer Sciences","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2135321730","https://openalex.org/W2797583228","https://openalex.org/W2936774411","https://openalex.org/W2962835968","https://openalex.org/W2982083293","https://openalex.org/W3030437843","https://openalex.org/W3163074978","https://openalex.org/W3196496149","https://openalex.org/W3198035615"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"This":[0],"paper":[1,18,40],"deals":[2],"with":[3,13],"the":[4,20,43,129,144,150,168,172,176],"problem":[5],"of":[6,67,86,93,131,146,152,155,170,179],"creating":[7,68],"a":[8,69,94],"keyword":[9],"spotting":[10],"(KWS)":[11],"system":[12,98],"real-world":[14],"audio":[15],"data.":[16,87,157],"The":[17,39],"describes":[19],"different":[21],"methods":[22],"used":[23,141],"to":[24,111,142],"build":[25],"KWS":[26,50,70,96,123,147,180],"systems,":[27],"deep":[28],"learning":[29],"models":[30,173],"such":[31],"as":[32],"convolutional":[33],"neural":[34,75],"networks":[35,76],"(CNN),":[36],"transformers,":[37],"etc.":[38],"also":[41,89,159],"discusses":[42],"mainstream":[44],"dataset":[45,62,71],"for":[46],"training":[47,81,156],"and":[48,63,72,104,116,134,174],"testing":[49],"models,":[51],"Google":[52,59],"Speech":[53,60],"Commands.":[54],"We":[55,88,118,158],"conduct":[56],"experiments":[57],"on":[58,82,166],"Commands":[61],"propose":[64],"our":[65],"method":[66,138],"that":[73,100,122,136,161],"helps":[74],"achieve":[77],"better":[78],"results":[79],"in":[80,109,128,149],"relatively":[83],"small":[84],"amounts":[85,154],"introduce":[90],"an":[91,125],"idea":[92],"hybrid":[95],"inference":[97],"architecture":[99],"uses":[101],"voice":[102],"detection":[103],"light-weight":[105],"speech":[106,132],"recognition":[107],"framework":[108],"attempt":[110],"boost":[112],"its":[113],"computational":[114],"performance":[115,145,178],"accuracy.":[117],"conclude":[119],"by":[120],"noting":[121],"is":[124],"important":[126],"challenge":[127],"field":[130],"recognition,":[133],"suggest":[135],"their":[137],"can":[139],"be":[140],"improve":[143],"systems":[148],"circumstances":[151],"low":[153],"note":[160],"future":[162],"research":[163],"could":[164],"focus":[165],"bettering":[167],"process":[169],"evaluating":[171],"improving":[175],"overall":[177],"systems.":[181]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}
