{"id":"https://openalex.org/W2903372879","doi":"https://doi.org/10.1109/icbslp.2018.8554395","title":"Bangla Short Speech Commands Recognition Using Convolutional Neural Networks","display_name":"Bangla Short Speech Commands Recognition Using Convolutional Neural Networks","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2903372879","doi":"https://doi.org/10.1109/icbslp.2018.8554395","mag":"2903372879"},"language":"en","primary_location":{"id":"doi:10.1109/icbslp.2018.8554395","doi":"https://doi.org/10.1109/icbslp.2018.8554395","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icbslp.2018.8554395","pdf_url":null,"source":{"id":"https://openalex.org/S7407106936","display_name":"International Conference on Bangla Speech and Language Processing (ICBSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference on Bangla Speech and Language Processing (ICBSLP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5002753957","display_name":"Shakil Ahmed Sumon","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157386601","display_name":"North South University","ror":"https://ror.org/05wdbfp45","country_code":"BD","type":"education","lineage":["https://openalex.org/I157386601"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Shakil Ahmed Sumon","raw_affiliation_strings":["Department of Electrical and Computer Engineering, North South University Plot-15, Bashundhara, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, North South University Plot-15, Bashundhara, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I157386601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014855879","display_name":"Joydip Chowdhury","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157386601","display_name":"North South University","ror":"https://ror.org/05wdbfp45","country_code":"BD","type":"education","lineage":["https://openalex.org/I157386601"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Joydip Chowdhury","raw_affiliation_strings":["Department of Electrical and Computer Engineering, North South University Plot-15, Bashundhara, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, North South University Plot-15, Bashundhara, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I157386601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072025867","display_name":"Sujit Debnath","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157386601","display_name":"North South University","ror":"https://ror.org/05wdbfp45","country_code":"BD","type":"education","lineage":["https://openalex.org/I157386601"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Sujit Debnath","raw_affiliation_strings":["Department of Electrical and Computer Engineering, North South University Plot-15, Bashundhara, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, North South University Plot-15, Bashundhara, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I157386601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062072064","display_name":"Nabeel Mohammed","orcid":"https://orcid.org/0000-0002-7661-3570","observed_orcids":["https://orcid.org/0000-0002-7661-3570"]},"institutions":[{"id":"https://openalex.org/I157386601","display_name":"North South University","ror":"https://ror.org/05wdbfp45","country_code":"BD","type":"education","lineage":["https://openalex.org/I157386601"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Nabeel Mohammed","raw_affiliation_strings":["Department of Electrical and Computer Engineering, North South University Plot-15, Bashundhara, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, North South University Plot-15, Bashundhara, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I157386601"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027844735","display_name":"Sifat Momen","orcid":"https://orcid.org/0000-0001-8683-7247","observed_orcids":["https://orcid.org/0000-0001-8683-7247"]},"institutions":[{"id":"https://openalex.org/I157386601","display_name":"North South University","ror":"https://ror.org/05wdbfp45","country_code":"BD","type":"education","lineage":["https://openalex.org/I157386601"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Sifat Momen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, North South University Plot-15, Bashundhara, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, North South University Plot-15, Bashundhara, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I157386601"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157386601"],"apc_list":null,"apc_paid":null,"fwci":1.3319,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.86840321,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.0003000000142492354,"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":9.999999747378752e-05,"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/bangla-speech-recognition","display_name":"Bangla speech recognition","score":0.9100000262260437},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.8190000057220459},{"id":"https://openalex.org/keywords/mel-frequency-cepstral-coefficients","display_name":"Mel-frequency cepstral coefficients","score":0.9639999866485596},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.8339999914169312},{"id":"https://openalex.org/keywords/fine-tuning-pre-trained-models","display_name":"pre-trained model fine-tuning","score":0.8330000042915344},{"id":"https://openalex.org/keywords/monosyllabic-words","display_name":"monosyllabic words","score":0.6140000224113464}],"concepts":[{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.891297459602356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8322798013687134},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7570940256118774},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6934599876403809},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6258254051208496},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.625045895576477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5353531837463379},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5234950184822083},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4088413715362549},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3160741925239563},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icbslp.2018.8554395","doi":"https://doi.org/10.1109/icbslp.2018.8554395","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icbslp.2018.8554395","pdf_url":null,"source":{"id":"https://openalex.org/S7407106936","display_name":"International Conference on Bangla Speech and Language Processing (ICBSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference on Bangla Speech and Language Processing (ICBSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W187290754","https://openalex.org/W1972567154","https://openalex.org/W1995562189","https://openalex.org/W2139231522","https://openalex.org/W2154068489","https://openalex.org/W2156387975","https://openalex.org/W2186860717","https://openalex.org/W2296748324","https://openalex.org/W2395106899","https://openalex.org/W2515753980","https://openalex.org/W2541700943","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3213399502","https://openalex.org/W3021306136","https://openalex.org/W4406984119","https://openalex.org/W3097539738","https://openalex.org/W4380189960","https://openalex.org/W2981283000","https://openalex.org/W3184668893","https://openalex.org/W4376108249","https://openalex.org/W2787249583","https://openalex.org/W3008762060"],"abstract_inverted_index":{"Despite":[0],"being":[1],"one":[2,91],"of":[3,9],"the":[4,10,30,54,59,87,95,135,149],"most":[5],"widely":[6],"spoken":[7],"languages":[8],"world,":[11],"no":[12],"significant":[13],"efforts":[14],"have":[15,69,83,99,161],"been":[16,50,70,84,100,123],"made":[17],"in":[18,36,58,90,102,141,164,172],"Bangla":[19,43,128,143],"speech":[20,45,76,118,145],"recognition.":[21],"Speech":[22],"recognition":[23],"is":[24,32,111,156],"a":[25,107,114],"difficult":[26],"task,":[27],"particularly":[28],"if":[29],"demand":[31],"to":[33,72],"do":[34],"so":[35],"noisy":[37],"real-life":[38,60],"conditions.":[39],"In":[40],"this":[41],"study,":[42],"short":[44,75,117,144],"commands":[46,119,146],"data":[47,120,129,155],"set":[48,121],"has":[49,122],"reported,":[51],"where":[52],"all":[53],"samples":[55],"are":[56],"taken":[57],"setting.":[61],"Three":[62],"different":[63],"convolutional":[64],"neural":[65],"network":[66],"(CNN)":[67],"architectures":[68],"designed":[71],"recognize":[73],"those":[74],"commands.":[77,175],"Mel-frequency":[78],"cepstral":[79],"coefficients":[80],"(MFCC)":[81],"features":[82],"extracted":[85],"from":[86],"audio":[88,97,154],"files":[89,98],"approach":[92],"whereas":[93],"only":[94],"raw":[96,153],"used":[101],"another":[103],"CNN":[104],"architecture.":[105],"Lastly,":[106],"pre-trained":[108],"model":[109,137,150],"which":[110],"trained":[112],"on":[113,127,152],"large":[115],"English":[116],"fine-tuned":[124],"by":[125],"retraining":[126],"set.":[130],"Experimental":[131],"results":[132],"reveal":[133],"that":[134],"MFCC":[136],"shows":[138],"better":[139],"accuracy":[140],"recognizing":[142,173],"where,":[147],"surprisingly,":[148],"predicting":[151],"very":[157],"competitive.":[158],"The":[159],"models":[160],"shown":[162],"proficiency":[163],"identifying":[165],"single":[166],"syllable":[167],"words":[168],"but":[169],"encounter":[170],"difficulties":[171],"multi-syllable":[174]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2018-12-11T00:00:00"}