{"id":"https://openalex.org/W2964187693","doi":"https://doi.org/10.1109/icassp.2018.8462688","title":"Deep Residual Learning for Small-Footprint Keyword Spotting","display_name":"Deep Residual Learning for Small-Footprint Keyword Spotting","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2964187693","doi":"https://doi.org/10.1109/icassp.2018.8462688","mag":"2964187693"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462688","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5101066425","display_name":"Raphael Tang","orcid":"https://orcid.org/0009-0007-2873-892X"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Raphael Tang","raw_affiliation_strings":["David R. Cheriton School of Computer Science, University of Waterloo"],"affiliations":[{"raw_affiliation_string":"David R. Cheriton School of Computer Science, University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jimmy Lin","raw_affiliation_strings":["David R. Cheriton School of Computer Science, University of Waterloo"],"affiliations":[{"raw_affiliation_string":"David R. Cheriton School of Computer Science, University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101066425"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":20.9835,"has_fulltext":false,"cited_by_count":225,"citation_normalized_percentile":{"value":0.994269,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5484","last_page":"5488"},"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.9987999796867371,"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/keyword-spotting","display_name":"Keyword spotting","score":0.927077054977417},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8518407940864563},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.8080480098724365},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7046029567718506},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6986475586891174},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.6958222985267639},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.6599130034446716},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.652093231678009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6306849122047424},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5327950119972229},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3664039969444275},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3582528829574585},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0601731538772583},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06006389856338501}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.927077054977417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8518407940864563},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.8080480098724365},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7046029567718506},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6986475586891174},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.6958222985267639},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.6599130034446716},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.652093231678009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6306849122047424},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5327950119972229},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3664039969444275},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3582528829574585},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0601731538772583},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06006389856338501},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462688","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":12,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W2034940213","https://openalex.org/W2194775991","https://openalex.org/W2407023693","https://openalex.org/W2747238065","https://openalex.org/W2765347007","https://openalex.org/W2916979304","https://openalex.org/W2953219395","https://openalex.org/W2963840672","https://openalex.org/W3098773154","https://openalex.org/W6714171909","https://openalex.org/W6726720044"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W1969408022","https://openalex.org/W2117995638"],"abstract_inverted_index":{"We":[0],"explore":[1],"the":[2,12,17,65,84],"application":[3],"of":[4,41,86],"deep":[5],"residual":[6,28],"learning":[7],"and":[8,47,74],"dilated":[9],"convolutions":[10],"to":[11,67,82],"keyword":[13,72],"spotting":[14],"task,":[15],"using":[16],"recently-released":[18],"Google":[19],"Speech":[20],"Commands":[21],"Dataset":[22],"as":[23],"our":[24,61,75],"benchmark.":[25],"Our":[26],"best":[27],"network":[29],"(ResNet)":[30],"implementation":[31],"significantly":[32],"outperforms":[33],"Google's":[34],"previous":[35,57],"convolutional":[36],"neural":[37],"networks":[38],"in":[39],"terms":[40],"accuracy.":[42],"By":[43],"varying":[44],"model":[45],"depth":[46],"width,":[48],"we":[49,63],"can":[50],"achieve":[51],"compact":[52],"models":[53],"that":[54],"also":[55],"outperform":[56],"small-footprint":[58],"variants.":[59],"To":[60],"knowledge,":[62],"are":[64],"first":[66],"examine":[68],"these":[69],"approaches":[70],"for":[71],"spotting,":[73],"results":[76],"establish":[77],"an":[78],"open-source":[79],"state-of-the-art":[80],"reference":[81],"support":[83],"development":[85],"future":[87],"speech-based":[88],"interfaces.":[89]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":31},{"year":2022,"cited_by_count":35},{"year":2021,"cited_by_count":50},{"year":2020,"cited_by_count":35},{"year":2019,"cited_by_count":35},{"year":2018,"cited_by_count":4}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}