{"id":"https://openalex.org/W4385215764","doi":"https://doi.org/10.1145/3606019","title":"End-to-end Multi-modal Low-resourced Speech Keywords Recognition Using Sequential Conv2D Nets","display_name":"End-to-end Multi-modal Low-resourced Speech Keywords Recognition Using Sequential Conv2D Nets","publication_year":2023,"publication_date":"2023-07-24","ids":{"openalex":"https://openalex.org/W4385215764","doi":"https://doi.org/10.1145/3606019"},"language":"en","primary_location":{"id":"doi:10.1145/3606019","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3606019","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","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/A5063568064","display_name":"Pooja Gambhir","orcid":"https://orcid.org/0000-0001-9299-1128"},"institutions":[{"id":"https://openalex.org/I20791572","display_name":"Indira Gandhi Institute of Technology","ror":"https://ror.org/0010jkx06","country_code":"IN","type":"education","lineage":["https://openalex.org/I20791572"]},{"id":"https://openalex.org/I4210143260","display_name":"Indira Gandhi Delhi Technical University for Women","ror":"https://ror.org/057c5p638","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210143260"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pooja Gambhir","raw_affiliation_strings":["Department of Information Technology, Indira Gandhi Delhi Technical University for Women, Kashmere Gate, New Delhi, India","Department of Information Technology, Indira Gandhi Delhi Technical University for Women, Kashmere Gate, New Delhi-110006, India"],"raw_orcid":"https://orcid.org/0000-0001-9299-1128","affiliations":[{"raw_affiliation_string":"Department of Information Technology, Indira Gandhi Delhi Technical University for Women, Kashmere Gate, New Delhi, India","institution_ids":["https://openalex.org/I20791572","https://openalex.org/I4210143260"]},{"raw_affiliation_string":"Department of Information Technology, Indira Gandhi Delhi Technical University for Women, Kashmere Gate, New Delhi-110006, India","institution_ids":["https://openalex.org/I20791572","https://openalex.org/I4210143260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022991626","display_name":"Amita Dev","orcid":"https://orcid.org/0000-0002-6926-9433"},"institutions":[{"id":"https://openalex.org/I20791572","display_name":"Indira Gandhi Institute of Technology","ror":"https://ror.org/0010jkx06","country_code":"IN","type":"education","lineage":["https://openalex.org/I20791572"]},{"id":"https://openalex.org/I4210143260","display_name":"Indira Gandhi Delhi Technical University for Women","ror":"https://ror.org/057c5p638","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210143260"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Amita Dev","raw_affiliation_strings":["Department of Information Technology, Indira Gandhi Delhi Technical University for Women, Kashmere Gate, New Delhi, India","Department of Information Technology, Indira Gandhi Delhi Technical University for Women, Kashmere Gate, New Delhi-110006, India"],"raw_orcid":"https://orcid.org/0000-0002-6926-9433","affiliations":[{"raw_affiliation_string":"Department of Information Technology, Indira Gandhi Delhi Technical University for Women, Kashmere Gate, New Delhi, India","institution_ids":["https://openalex.org/I20791572","https://openalex.org/I4210143260"]},{"raw_affiliation_string":"Department of Information Technology, Indira Gandhi Delhi Technical University for Women, Kashmere Gate, New Delhi-110006, India","institution_ids":["https://openalex.org/I20791572","https://openalex.org/I4210143260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102886753","display_name":"Poonam Bansal","orcid":"https://orcid.org/0000-0002-8214-2840"},"institutions":[{"id":"https://openalex.org/I20791572","display_name":"Indira Gandhi Institute of Technology","ror":"https://ror.org/0010jkx06","country_code":"IN","type":"education","lineage":["https://openalex.org/I20791572"]},{"id":"https://openalex.org/I4210143260","display_name":"Indira Gandhi Delhi Technical University for Women","ror":"https://ror.org/057c5p638","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210143260"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Poonam Bansal","raw_affiliation_strings":["Department of Information Technology, Indira Gandhi Delhi Technical University for Women, Kashmere Gate, New Delhi, India","Department of Information Technology, Indira Gandhi Delhi Technical University for Women, Kashmere Gate, New Delhi-110006, India"],"raw_orcid":"https://orcid.org/0000-0002-8214-2840","affiliations":[{"raw_affiliation_string":"Department of Information Technology, Indira Gandhi Delhi Technical University for Women, Kashmere Gate, New Delhi, India","institution_ids":["https://openalex.org/I20791572","https://openalex.org/I4210143260"]},{"raw_affiliation_string":"Department of Information Technology, Indira Gandhi Delhi Technical University for Women, Kashmere Gate, New Delhi-110006, India","institution_ids":["https://openalex.org/I20791572","https://openalex.org/I4210143260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037529623","display_name":"Deepak Kumar Sharma","orcid":"https://orcid.org/0000-0001-6117-3464"},"institutions":[{"id":"https://openalex.org/I20791572","display_name":"Indira Gandhi Institute of Technology","ror":"https://ror.org/0010jkx06","country_code":"IN","type":"education","lineage":["https://openalex.org/I20791572"]},{"id":"https://openalex.org/I4210143260","display_name":"Indira Gandhi Delhi Technical University for Women","ror":"https://ror.org/057c5p638","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210143260"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Deepak Kumar Sharma","raw_affiliation_strings":["Department of Information Technology, Indira Gandhi Delhi Technical University for Women, Kashmere Gate, New Delhi, India","Department of Information Technology, Indira Gandhi Delhi Technical University for Women, Kashmere Gate, New Delhi-110006, India"],"raw_orcid":"https://orcid.org/0000-0001-6117-3464","affiliations":[{"raw_affiliation_string":"Department of Information Technology, Indira Gandhi Delhi Technical University for Women, Kashmere Gate, New Delhi, India","institution_ids":["https://openalex.org/I20791572","https://openalex.org/I4210143260"]},{"raw_affiliation_string":"Department of Information Technology, Indira Gandhi Delhi Technical University for Women, Kashmere Gate, New Delhi-110006, India","institution_ids":["https://openalex.org/I20791572","https://openalex.org/I4210143260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7948,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.87899037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"23","issue":"1","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.9990000128746033,"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":0.7935699820518494},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7852879762649536},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7448077201843262},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6216530799865723},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.6149600744247437},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5648674964904785},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.513794481754303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4744480848312378},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.46548619866371155},{"id":"https://openalex.org/keywords/hindi","display_name":"Hindi","score":0.4441649615764618},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4104461073875427},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37752118706703186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7935699820518494},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7852879762649536},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7448077201843262},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6216530799865723},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.6149600744247437},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5648674964904785},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.513794481754303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4744480848312378},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.46548619866371155},{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.4441649615764618},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4104461073875427},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37752118706703186},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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":[{"id":"doi:10.1145/3606019","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3606019","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"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":28,"referenced_works":["https://openalex.org/W1992506798","https://openalex.org/W1995562189","https://openalex.org/W2103088716","https://openalex.org/W2106560396","https://openalex.org/W2119569779","https://openalex.org/W2147768505","https://openalex.org/W2161329381","https://openalex.org/W2168609109","https://openalex.org/W2254811285","https://openalex.org/W2400957076","https://openalex.org/W2401869809","https://openalex.org/W2530400070","https://openalex.org/W2566781703","https://openalex.org/W2599825545","https://openalex.org/W2606429533","https://openalex.org/W2790641317","https://openalex.org/W2889367800","https://openalex.org/W2913178639","https://openalex.org/W2919448963","https://openalex.org/W2962146825","https://openalex.org/W2963403664","https://openalex.org/W2963827914","https://openalex.org/W3022365677","https://openalex.org/W3092996096","https://openalex.org/W3197051898","https://openalex.org/W4247765127","https://openalex.org/W6692326255","https://openalex.org/W6931136213"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2160511961","https://openalex.org/W4317383455"],"abstract_inverted_index":{"Advanced":[0],"Neural":[1,19],"Networks":[2],"are":[3],"widely":[4],"used":[5],"to":[6,164],"recognize":[7],"multi-modal":[8],"conversational":[9],"speech":[10,74,108,117,134],"with":[11,121,160],"significant":[12,152],"improvements":[13],"in":[14,25,33,51,167,187],"accuracy":[15,180],"automatically.":[16],"Significantly,":[17],"Convolutional":[18,60,155],"sheets":[20],"have":[21],"retreated":[22],"cutting-edge":[23],"performance":[24,153],"Automatic":[26],"Voice":[27],"Recognition":[28],"(AVR)":[29],"recently":[30],"more":[31],"appropriately":[32],"English;":[34],"however,":[35],"the":[36,149,176],"Hindi":[37,120,184],"language":[38],"has":[39,54,82],"not":[40],"been":[41,83],"explored":[42],"and":[43,77,85,94,104,128,139],"examined":[44],"well":[45],"on":[46,87,114,158],"AVR":[47],"systems.":[48],"The":[49,63,80,110,144],"work":[50],"this":[52],"article":[53],"exposed":[55],"a":[56],"three-layered":[57],"two-dimensional":[58],"Sequential":[59,64],"neural":[61],"architecture.":[62],"Conv2D":[65],"is":[66],"an":[67,179],"end-to-end":[68],"system":[69],"that":[70,148,165],"can":[71],"instantaneously":[72],"exploit":[73],"signal":[75],"spectral":[76],"temporal":[78],"structures.":[79,109],"network":[81],"trained":[84,157],"tested":[86],"different":[88],"cepstral":[89,169,190],"features":[90,106,192],"such":[91],"as":[92],"Frequency":[93],"Time":[95],"variant-Mel-Filters,":[96],"Gamma-tone":[97],"Filter":[98],"Cepstral":[99],"Quantities,":[100],"Bark-Filter":[101],"band":[102],"Coefficients,":[103],"Spectrogram":[105],"of":[107,132,154,181],"experiment":[111],"was":[112],"performed":[113],"two":[115],"low-resourced":[116],"command":[118],"datasets;":[119],"27,145":[122],"Speech":[123,142],"Keywords":[124],"developed":[125],"by":[126,136],"TIFR":[127],"23,664":[129],"(1-s":[130],"utterances)":[131],"English":[133,141,173],"commands":[135],"Google":[137],"TensorFlow":[138],"AIY":[140],"Commands.":[143],"experimental":[145],"outcome":[146],"showed":[147],"model":[150,177],"achieves":[151],"layers":[156],"spectrograms":[159],"91.60%":[161],"accuracy,":[162],"compared":[163],"achieved":[166,178],"other":[168],"feature":[170],"labels":[171],"for":[172,183],"speech.":[174],"However,":[175],"69.65%":[182],"audio":[185],"words":[186],"which":[188],"bark-frequency":[189],"coefficients":[191],"outperformed":[193],"spectrogram":[194],"features.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}