{"id":"https://openalex.org/W4372267500","doi":"https://doi.org/10.1109/icassp49357.2023.10096736","title":"Wekws: A Production First Small-Footprint End-to-End Keyword Spotting Toolkit","display_name":"Wekws: A Production First Small-Footprint End-to-End Keyword Spotting Toolkit","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267500","doi":"https://doi.org/10.1109/icassp49357.2023.10096736"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5100440069","display_name":"Jie Wang","orcid":"https://orcid.org/0000-0002-3023-3804"},"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":"Jie Wang","raw_affiliation_strings":["Northwestern Polytechnical University,School of Marine Science and Technology,Xi’an,China","WeNet Open Source Community"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Marine Science and Technology,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112501143","display_name":"Menglong Xu","orcid":"https://orcid.org/0009-0001-5860-8532"},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Menglong Xu","raw_affiliation_strings":["Horizon Robotics,Beijing,China","WeNet Open Source Community","Horizon Robotics, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Horizon Robotics,Beijing,China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]},{"raw_affiliation_string":"Horizon Robotics, Beijing, China","institution_ids":["https://openalex.org/I4401726824"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018722799","display_name":"Jingyong Hou","orcid":"https://orcid.org/0000-0002-1861-7776"},"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":"Jingyong Hou","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","WeNet Open Source Community"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449711","display_name":"Binbin Zhang","orcid":"https://orcid.org/0000-0002-1345-2220"},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binbin Zhang","raw_affiliation_strings":["Horizon Robotics,Beijing,China","Horizon Robotics, Beijing, China","WeNet Open Source Community"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Horizon Robotics,Beijing,China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"Horizon Robotics, Beijing, China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450091","display_name":"Xiao-Lei Zhang","orcid":"https://orcid.org/0000-0001-7694-193X"},"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":"Xiao-Lei Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,School of Marine Science and Technology,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Marine Science and Technology,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","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":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031150833","display_name":"Fuping Pan","orcid":"https://orcid.org/0000-0001-9171-0726"},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuping Pan","raw_affiliation_strings":["Horizon Robotics,Beijing,China","Horizon Robotics, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Horizon Robotics,Beijing,China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"Horizon Robotics, Beijing, China","institution_ids":["https://openalex.org/I4401726824"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6316,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86589023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9976000189781189,"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/T10028","display_name":"Topic Modeling","score":0.9976000189781189,"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/T12031","display_name":"Speech and dialogue systems","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8790953159332275},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.7959754467010498},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7503753900527954},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.7427979707717896},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7334781289100647},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.6929766535758972},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6133014559745789},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5779176354408264},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.5235031247138977},{"id":"https://openalex.org/keywords/end-user","display_name":"End user","score":0.4984257221221924},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.49039459228515625},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4650861620903015},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.4197905659675598},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3281405568122864},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.212313711643219},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.17971208691596985},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17284256219863892}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8790953159332275},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.7959754467010498},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7503753900527954},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7427979707717896},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7334781289100647},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6929766535758972},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6133014559745789},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5779176354408264},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.5235031247138977},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.4984257221221924},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.49039459228515625},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4650861620903015},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.4197905659675598},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3281405568122864},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.212313711643219},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.17971208691596985},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17284256219863892},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1544266773","https://openalex.org/W2034940213","https://openalex.org/W2587529061","https://openalex.org/W2765347007","https://openalex.org/W2792764867","https://openalex.org/W2797583228","https://openalex.org/W2910655080","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2963414149","https://openalex.org/W2963628261","https://openalex.org/W2964187693","https://openalex.org/W2972792496","https://openalex.org/W3015287265","https://openalex.org/W3016238098","https://openalex.org/W3094791070","https://openalex.org/W3096421563","https://openalex.org/W3098773154","https://openalex.org/W3160521245","https://openalex.org/W3163237592","https://openalex.org/W3197478142","https://openalex.org/W4220809630","https://openalex.org/W4224916413","https://openalex.org/W4225311910","https://openalex.org/W6631362777","https://openalex.org/W6632425017","https://openalex.org/W6745159674","https://openalex.org/W6749714907","https://openalex.org/W6749825310","https://openalex.org/W6750665317","https://openalex.org/W6761305474","https://openalex.org/W6784696928"],"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":{"Keyword":[0],"spotting":[1],"(KWS)":[2],"enables":[3],"speech-based":[4],"user":[5],"interaction":[6],"and":[7,39,54,111],"gradually":[8],"becomes":[9],"an":[10],"indispensable":[11],"component":[12],"of":[13,41,63,100],"smart":[14],"devices.":[15],"Recently,":[16],"end-to-end":[17],"(E2E)":[18],"methods":[19],"have":[20],"be-come":[21],"the":[22,37,61,94,97,101,108],"most":[23],"popular":[24],"approach":[25],"for":[26],"on-device":[27],"KWS":[28,43,57],"tasks.":[29],"However,":[30],"there":[31],"is":[32,124],"still":[33],"a":[34,51,82,88],"gap":[35],"between":[36],"research":[38],"deployment":[40],"E2E":[42,56,84],"methods.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,86],"introduce":[49],"WeKws,":[50],"production-quality,":[52],"easy-to-build,":[53],"convenient-to-be-applied":[55],"toolkit.":[58],"WeKws":[59,81,113],"contains":[60],"implementations":[62],"several":[64],"state-of-the-art":[65],"backbone":[66],"networks,":[67],"making":[68],"it":[69],"achieve":[70],"highly":[71],"competitive":[72],"results":[73],"on":[74],"three":[75],"publicly":[76,125],"available":[77,126],"datasets.":[78],"To":[79],"make":[80,93],"pure":[83],"toolkit,":[85],"utilize":[87],"refined":[89],"max-pooling":[90],"loss":[91],"to":[92,116],"model":[95],"learn":[96],"ending":[98],"position":[99],"keyword":[102],"by":[103],"itself,":[104],"which":[105],"significantly":[106],"simplifies":[107],"training":[109],"pipeline":[110],"makes":[112],"very":[114],"efficient":[115],"be":[117],"applied":[118],"in":[119],"real-world":[120],"scenarios.":[121],"The":[122],"toolkit":[123],"at":[127],"https://github.com/wenet-e2e/wekws.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}