{"id":"https://openalex.org/W2963414149","doi":"https://doi.org/10.21437/interspeech.2018-1777","title":"Attention-based End-to-End Models for Small-Footprint Keyword Spotting","display_name":"Attention-based End-to-End Models for Small-Footprint Keyword Spotting","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2963414149","doi":"https://doi.org/10.21437/interspeech.2018-1777","mag":"2963414149"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1777","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/A5042775692","display_name":"Changhao Shan","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Changhao Shan","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China","Xiaomi Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Xiaomi Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778479","display_name":"Junbo Zhang","orcid":"https://orcid.org/0000-0001-5947-1374"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junbo Zhang","raw_affiliation_strings":["Xiaomi Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362608","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0003-2335-0946"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":["Xiaomi Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Inc., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5042775692"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":9.7731,"has_fulltext":false,"cited_by_count":99,"citation_normalized_percentile":{"value":0.9838838,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9952999949455261,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9952999949455261,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9850999712944031,"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":0.9836999773979187,"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/footprint","display_name":"Footprint","score":0.7898730635643005},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.7873681783676147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7537554502487183},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.7470818758010864},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6801612377166748},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24755233526229858},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0786040723323822}],"concepts":[{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.7898730635643005},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.7873681783676147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7537554502487183},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.7470818758010864},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6801612377166748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24755233526229858},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0786040723323822},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2018-1777","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1600744878","https://openalex.org/W2034940213","https://openalex.org/W2056986588","https://openalex.org/W2109886035","https://openalex.org/W2133564696","https://openalex.org/W2145215282","https://openalex.org/W2157331557","https://openalex.org/W2167338739","https://openalex.org/W2212465773","https://openalex.org/W2327501763","https://openalex.org/W2405666970","https://openalex.org/W2697044473","https://openalex.org/W2953219395","https://openalex.org/W2962707338","https://openalex.org/W2962959915","https://openalex.org/W2962965405","https://openalex.org/W2963881567","https://openalex.org/W3098773154"],"related_works":["https://openalex.org/W2742860341","https://openalex.org/W4308521107","https://openalex.org/W4248007934","https://openalex.org/W3018114492","https://openalex.org/W1554833030","https://openalex.org/W2323788589","https://openalex.org/W4385822657","https://openalex.org/W2938873567","https://openalex.org/W2963414149","https://openalex.org/W4372267500"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"an":[5,30,33],"attention-based":[6,121],"end-to-end":[7],"neural":[8],"approach":[9,95,101],"for":[10,72],"small-footprint":[11],"keyword":[12,73],"spotting":[13],"(KWS),":[14],"which":[15],"aims":[16],"to":[17],"simplify":[18],"the":[19,38,48,52,66,77,97,107],"pipelines":[20],"of":[21,29,79],"building":[22],"a":[23,42,57,69,103],"production-quality":[24],"KWS":[25,100],"system.Our":[26],"model":[27,122],"consists":[28],"encoder":[31,36,53,81],"and":[32,55,63,86,106],"attention":[34,49],"mechanism.The":[35],"transforms":[37],"input":[39],"signal":[40],"into":[41],"high":[43],"level":[44],"representation":[45],"using":[46],"RNNs.Then":[47],"mechanism":[50],"weights":[51],"features":[54],"generates":[56],"fixed-length":[58],"vector.Finally,":[59],"by":[60,102,112],"linear":[61],"transformation":[62],"softmax":[64],"function,":[65],"vector":[67],"becomes":[68],"score":[70],"used":[71],"detection.We":[74],"also":[75],"evaluate":[76],"performance":[78,109],"different":[80],"architectures,":[82],"including":[83],"LSTM,":[84],"GRU":[85],"CRNN.Experiments":[87],"on":[88],"real-world":[89],"wake-up":[90],"data":[91],"show":[92],"that":[93],"our":[94,120],"outperforms":[96],"recent":[98],"Deep":[99],"large":[104],"margin":[105],"best":[108],"is":[110],"achieved":[111],"CRNN.To":[113],"be":[114],"more":[115],"specific,":[116],"with":[117],"\u223c84K":[118],"parameters,":[119],"achieves":[123],"1.02%":[124],"false":[125,131],"rejection":[126],"rate":[127],"(FRR)":[128],"at":[129],"1.0":[130],"alarm":[132],"(FA)":[133],"per":[134],"hour.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}