{"id":"https://openalex.org/W3033387233","doi":"https://doi.org/10.1145/3386164.3389100","title":"Image Approach to Speech Recognition on CNN","display_name":"Image Approach to Speech Recognition on CNN","publication_year":2019,"publication_date":"2019-09-25","ids":{"openalex":"https://openalex.org/W3033387233","doi":"https://doi.org/10.1145/3386164.3389100","mag":"3033387233"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3386164.3389100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5039079344","display_name":"Muhammadjon Musaev","orcid":"https://orcid.org/0000-0002-9355-0954"},"institutions":[{"id":"https://openalex.org/I21256249","display_name":"Tashkent University of Information Technology","ror":"https://ror.org/05987a729","country_code":"UZ","type":"education","lineage":["https://openalex.org/I21256249"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Muhammadjon Musaev","raw_affiliation_strings":["Computer Systems, Tashkent University of Information technologies named after, Muhammad Al-Khwarizmi, Tashkent, Uzbekistan"],"affiliations":[{"raw_affiliation_string":"Computer Systems, Tashkent University of Information technologies named after, Muhammad Al-Khwarizmi, Tashkent, Uzbekistan","institution_ids":["https://openalex.org/I21256249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088308540","display_name":"Ilyos Khujayorov","orcid":"https://orcid.org/0000-0002-0573-6303"},"institutions":[{"id":"https://openalex.org/I21256249","display_name":"Tashkent University of Information Technology","ror":"https://ror.org/05987a729","country_code":"UZ","type":"education","lineage":["https://openalex.org/I21256249"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Ilyos Khujayorov","raw_affiliation_strings":["Computer Systems, Tashkent University of Information technologies named after, Muhammad Al-Khwarizmi, Tashkent, Uzbekistan"],"affiliations":[{"raw_affiliation_string":"Computer Systems, Tashkent University of Information technologies named after, Muhammad Al-Khwarizmi, Tashkent, Uzbekistan","institution_ids":["https://openalex.org/I21256249"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041720832","display_name":"Mannon Ochilov","orcid":"https://orcid.org/0000-0002-8330-0855"},"institutions":[{"id":"https://openalex.org/I21256249","display_name":"Tashkent University of Information Technology","ror":"https://ror.org/05987a729","country_code":"UZ","type":"education","lineage":["https://openalex.org/I21256249"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Mannon Ochilov","raw_affiliation_strings":["Computer Systems, Tashkent University of Information technologies named after, Muhammad Al-Khwarizmi, Tashkent, Uzbekistan"],"affiliations":[{"raw_affiliation_string":"Computer Systems, Tashkent University of Information technologies named after, Muhammad Al-Khwarizmi, Tashkent, Uzbekistan","institution_ids":["https://openalex.org/I21256249"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.207,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.772071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9965,"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/T10860","display_name":"Speech and Audio Processing","score":0.9965,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962,"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":0.9937,"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/spectrogram","display_name":"Spectrogram","score":0.9374331},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7391763},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6779108},{"id":"https://openalex.org/keywords/uzbek","display_name":"Uzbek","score":0.64407647}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9374331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77560514},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7391763},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6820468},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6779108},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6651925},{"id":"https://openalex.org/C2778718127","wikidata":"https://www.wikidata.org/wiki/Q9264","display_name":"Uzbek","level":2,"score":0.64407647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.63532186},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5085},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4658343},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44512084},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43747473},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07402289},{"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":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3386164.3389100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.73}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":24,"referenced_works":["https://openalex.org/W1572063013","https://openalex.org/W1994216910","https://openalex.org/W2020351623","https://openalex.org/W2084514013","https://openalex.org/W2095705004","https://openalex.org/W2100616526","https://openalex.org/W2117671523","https://openalex.org/W2124510467","https://openalex.org/W2323591384","https://openalex.org/W2431323835","https://openalex.org/W2599132251","https://openalex.org/W2609598179","https://openalex.org/W2751841560","https://openalex.org/W2755245168","https://openalex.org/W2780038876","https://openalex.org/W2792325916","https://openalex.org/W2900263579","https://openalex.org/W2949117887","https://openalex.org/W2964121744","https://openalex.org/W2996731350","https://openalex.org/W3139732350","https://openalex.org/W4205130185","https://openalex.org/W4206946539","https://openalex.org/W4297792748"],"related_works":["https://openalex.org/W4400096497","https://openalex.org/W4387384108","https://openalex.org/W4386412192","https://openalex.org/W4287102325","https://openalex.org/W4233671716","https://openalex.org/W3125445824","https://openalex.org/W3109143930","https://openalex.org/W3005658041","https://openalex.org/W2992378700","https://openalex.org/W2964954556"],"abstract_inverted_index":{"In":[0,62],"this":[1],"paper":[2],"has":[3],"been":[4],"discussed":[5],"about":[6],"speech":[7,24],"recognition":[8],"using":[9],"spectrogram":[10,57],"images":[11,22,58],"and":[12,28,43,54,73],"deep":[13,33],"convolution":[14,41],"neural":[15],"network(CNN)":[16],"of":[17,56,67],"Uzbek":[18,68,90],"spoken":[19,69,91],"digits.":[20],"Spectrogram":[21],"from":[23],"signal":[25],"were":[26,30,71,81],"generated":[27],"it":[29],"used":[31],"for":[32,89],"CNN":[34,37,78],"training.":[35],"Presented":[36],"model":[38,79],"contains":[39],"3":[40],"layers":[42,47],"2":[44],"fully":[45],"connected":[46],"that":[48],"discriminative":[49],"features":[50],"can":[51],"be":[52],"divided":[53],"estimated":[55],"by":[59],"those":[60],"layers.":[61],"current":[63],"research":[64],"period,":[65],"dataset":[66],"digits":[70,92],"made":[72],"in":[74],"based":[75],"on":[76],"presented":[77],"they":[80],"trained.":[82],"Testing":[83],"results":[84],"shows":[85],"that,":[86],"proposed":[87],"approach":[88],"classified":[93],"100%":[94],"accuracy.":[95]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3033387233","counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5}],"updated_date":"2025-01-18T09:14:21.632480","created_date":"2020-06-12"}