{"id":"https://openalex.org/W3016172026","doi":"https://doi.org/10.1109/icassp40776.2020.9053970","title":"Bangla Voice Command Recognition in end-to-end System Using Topic Modeling based Contextual Rescoring","display_name":"Bangla Voice Command Recognition in end-to-end System Using Topic Modeling based Contextual Rescoring","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016172026","doi":"https://doi.org/10.1109/icassp40776.2020.9053970","mag":"3016172026"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5019517211","display_name":"Nafis Sadeq","orcid":"https://orcid.org/0000-0002-2596-2340"},"institutions":[{"id":"https://openalex.org/I183697816","display_name":"Bangladesh University of Engineering and Technology","ror":"https://ror.org/05a1qpv97","country_code":"BD","type":"education","lineage":["https://openalex.org/I183697816"]}],"countries":["BD"],"is_corresponding":true,"raw_author_name":"Nafis Sadeq","raw_affiliation_strings":["Bangladesh University of Engineering and Technology (BUET)"],"affiliations":[{"raw_affiliation_string":"Bangladesh University of Engineering and Technology (BUET)","institution_ids":["https://openalex.org/I183697816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058975650","display_name":"Shafayat Ahmed","orcid":null},"institutions":[{"id":"https://openalex.org/I183697816","display_name":"Bangladesh University of Engineering and Technology","ror":"https://ror.org/05a1qpv97","country_code":"BD","type":"education","lineage":["https://openalex.org/I183697816"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Shafayat Ahmed","raw_affiliation_strings":["Bangladesh University of Engineering and Technology (BUET)"],"affiliations":[{"raw_affiliation_string":"Bangladesh University of Engineering and Technology (BUET)","institution_ids":["https://openalex.org/I183697816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103080820","display_name":"Sudipta Saha Shubha","orcid":"https://orcid.org/0009-0002-9284-507X"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sudipta Saha Shubha","raw_affiliation_strings":["University of Virginia"],"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017772584","display_name":"Md. Nahidul Islam","orcid":"https://orcid.org/0000-0002-2797-410X"},"institutions":[{"id":"https://openalex.org/I183697816","display_name":"Bangladesh University of Engineering and Technology","ror":"https://ror.org/05a1qpv97","country_code":"BD","type":"education","lineage":["https://openalex.org/I183697816"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Md. Nahidul Islam","raw_affiliation_strings":["Bangladesh University of Engineering and Technology (BUET)"],"affiliations":[{"raw_affiliation_string":"Bangladesh University of Engineering and Technology (BUET)","institution_ids":["https://openalex.org/I183697816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059669108","display_name":"Muhammad Abdullah Adnan","orcid":"https://orcid.org/0000-0003-3219-9053"},"institutions":[{"id":"https://openalex.org/I183697816","display_name":"Bangladesh University of Engineering and Technology","ror":"https://ror.org/05a1qpv97","country_code":"BD","type":"education","lineage":["https://openalex.org/I183697816"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Muhammad Abdullah Adnan","raw_affiliation_strings":["Bangladesh University of Engineering and Technology (BUET)"],"affiliations":[{"raw_affiliation_string":"Bangladesh University of Engineering and Technology (BUET)","institution_ids":["https://openalex.org/I183697816"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5019517211"],"corresponding_institution_ids":["https://openalex.org/I183697816"],"apc_list":null,"apc_paid":null,"fwci":0.7954,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77712175,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9955000281333923,"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":0.995199978351593,"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":0.8798918724060059},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.751087486743927},{"id":"https://openalex.org/keywords/bengali","display_name":"Bengali","score":0.7480469942092896},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6955136060714722},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6690312623977661},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6554185152053833},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6289078593254089},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6076076626777649},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5318046808242798},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.524520993232727},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46614399552345276},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.46302762627601624},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4410477876663208},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4282551109790802},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36132097244262695},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.16575747728347778}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8798918724060059},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.751087486743927},{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.7480469942092896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6955136060714722},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6690312623977661},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6554185152053833},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6289078593254089},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6076076626777649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5318046808242798},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.524520993232727},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46614399552345276},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.46302762627601624},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4410477876663208},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4282551109790802},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36132097244262695},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.16575747728347778},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W64751979","https://openalex.org/W1969486090","https://openalex.org/W1999965501","https://openalex.org/W2395440424","https://openalex.org/W2403440562","https://openalex.org/W2586813637","https://openalex.org/W2586988759","https://openalex.org/W2627092829","https://openalex.org/W2766219058","https://openalex.org/W2886025712","https://openalex.org/W2888975141","https://openalex.org/W2889012072","https://openalex.org/W2895676041","https://openalex.org/W2903250132","https://openalex.org/W6602670161","https://openalex.org/W6713395095"],"related_works":["https://openalex.org/W2084490135","https://openalex.org/W2895890526","https://openalex.org/W4298170800","https://openalex.org/W2794758919","https://openalex.org/W617692174","https://openalex.org/W4232781930","https://openalex.org/W1913642778","https://openalex.org/W4300860228","https://openalex.org/W2630858571","https://openalex.org/W2329406070"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"perform":[4],"contextual":[5,55],"rescoring":[6,62],"using":[7],"multi-label":[8],"topic":[9],"modeling":[10],"to":[11,71],"improve":[12],"the":[13,80],"performance":[14,91],"of":[15,27],"an":[16],"End-to-End":[17,37],"Bangla":[18,74],"voice":[19,75],"command":[20,76],"recognition":[21,77],"system.":[22],"We":[23,39],"use":[24,40],"a":[25],"hybrid":[26],"Connectionist":[28],"Temporal":[29],"Classification":[30],"(CTC)":[31],"and":[32,48],"Attention":[33],"mechanism":[34],"in":[35,73],"our":[36,61],"architecture.":[38],"Recurrent":[41],"Neural":[42],"Network":[43],"(RNN)":[44],"as":[45],"language":[46],"model":[47],"La-beled":[49],"LDA":[50],"(Latent":[51],"Dirichlet":[52],"allocation)":[53],"for":[54],"rescoring.":[56],"Our":[57],"experiments":[58],"show":[59],"that":[60],"method":[63],"reduces":[64],"Word":[65],"Error":[66],"Rate":[67],"(WER)":[68],"from":[69],"16.7%":[70],"12.8%":[72],"task":[78],"when":[79,92],"relevant":[81],"context":[82,94],"is":[83,95],"provided.":[84,96],"The":[85],"system":[86],"does":[87],"not":[88],"lose":[89],"any":[90],"irrelevant":[93]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
