{"id":"https://openalex.org/W2972951785","doi":"https://doi.org/10.21437/interspeech.2019-1766","title":"Sub-Band Convolutional Neural Networks for Small-Footprint Spoken Term Classification","display_name":"Sub-Band Convolutional Neural Networks for Small-Footprint Spoken Term Classification","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972951785","doi":"https://doi.org/10.21437/interspeech.2019-1766","mag":"2972951785"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1766","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","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/A5020775828","display_name":"Chieh-Chi Kao","orcid":"https://orcid.org/0000-0002-1161-3959"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chieh-Chi Kao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755311","display_name":"Ming Sun","orcid":"https://orcid.org/0000-0002-5948-2708"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101781558","display_name":"Yixin Gao","orcid":"https://orcid.org/0000-0001-8854-8959"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixin Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069416097","display_name":"Shiv Vitaladevuni","orcid":"https://orcid.org/0000-0003-2709-5145"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiv Vitaladevuni","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100406950","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0002-1560-6182"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3121,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.86213618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2195","last_page":"2199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9970999956130981,"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":0.9970999956130981,"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":0.9970999956130981,"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":0.9894000291824341,"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7502855658531189},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.7385317087173462},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7328460216522217},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.7040402889251709},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5184885263442993},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43713632225990295},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.11555129289627075}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7502855658531189},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.7385317087173462},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7328460216522217},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.7040402889251709},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5184885263442993},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43713632225990295},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.11555129289627075},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-1766","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2034940213","https://openalex.org/W2155273149","https://openalex.org/W2188183693","https://openalex.org/W2407023693","https://openalex.org/W2507580616","https://openalex.org/W2515753980","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2726515241","https://openalex.org/W2748659049","https://openalex.org/W2775505379","https://openalex.org/W2797583228","https://openalex.org/W2808631503","https://openalex.org/W2889129739","https://openalex.org/W2938357656","https://openalex.org/W2939302994","https://openalex.org/W2953219395","https://openalex.org/W2962707338","https://openalex.org/W2962711843","https://openalex.org/W2963543871","https://openalex.org/W2963750251","https://openalex.org/W2963864497","https://openalex.org/W2964066126","https://openalex.org/W2964187693","https://openalex.org/W2972384212"],"related_works":["https://openalex.org/W2330537534","https://openalex.org/W4293226380","https://openalex.org/W2368534554","https://openalex.org/W2730343163","https://openalex.org/W2148469257","https://openalex.org/W2168827721","https://openalex.org/W2319969327","https://openalex.org/W42295635","https://openalex.org/W2581881485","https://openalex.org/W1973996291"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,59,64,76,113,123],"Sub-band":[4],"Convolutional":[5],"Neural":[6],"Network":[7],"for":[8,109,118],"spoken":[9,26,119],"term":[10,27,120],"classification.Convolutional":[11],"neural":[12],"networks":[13],"(CNNs)":[14],"have":[15],"proven":[16],"to":[17,80,112],"be":[18],"very":[19],"effective":[20],"in":[21,38,70],"acoustic":[22,33,52],"applications":[23,37,53],"such":[24],"as":[25],"classification,":[28,141],"keyword":[29],"spotting,":[30],"speaker":[31],"identification,":[32],"event":[34],"detection,":[35],"etc.Unlike":[36],"computer":[39],"vision,":[40],"the":[41,56,67,91,99,129,135],"spatial":[42],"invariance":[43],"property":[44],"of":[45,58],"2D":[46,61],"convolutional":[47,83],"kernels":[48,84],"does":[49],"not":[50],"fit":[51],"well":[54],"since":[55],"meaning":[57],"specific":[60],"kernel":[62],"varies":[63],"lot":[65],"along":[66],"feature":[68,73,87],"axis":[69],"an":[71],"input":[72],"map.We":[74],"propose":[75],"sub-band":[77,104,131],"CNN":[78,105,117,132],"architecture":[79,133],"apply":[81],"different":[82],"on":[85,122,139,144],"each":[86],"sub-band,":[88],"which":[89],"makes":[90],"overall":[92],"computation":[93,136],"more":[94,107],"efficient.Experimental":[95],"results":[96],"show":[97],"that":[98],"computational":[100],"efficiency":[101],"brought":[102],"by":[103,137],"is":[106],"beneficial":[108],"smallfootprint":[110],"models.Compared":[111],"baseline":[114],"full":[115],"band":[116],"classification":[121,146],"publicly":[124],"available":[125],"Speech":[126],"Commands":[127],"dataset,":[128],"proposed":[130],"reduces":[134],"39.7%":[138],"commands":[140],"and":[142],"49.3%":[143],"digits":[145],"with":[147],"accuracy":[148],"maintained.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}