{"id":"https://openalex.org/W4210820152","doi":"https://doi.org/10.1109/asru51503.2021.9688326","title":"An End-to-End Far-Field Keyword Spotting System with Neural Beamforming","display_name":"An End-to-End Far-Field Keyword Spotting System with Neural Beamforming","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210820152","doi":"https://doi.org/10.1109/asru51503.2021.9688326"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688326","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5110930567","display_name":"Xuan Ji","orcid":"https://orcid.org/0009-0008-1913-5219"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuan Ji","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100366031","display_name":"Lu Lu","orcid":"https://orcid.org/0000-0002-6077-0977"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lu Lu","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012466506","display_name":"Fuming Fang","orcid":"https://orcid.org/0000-0002-9332-3735"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fuming Fang","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102822627","display_name":"Jianbo Ma","orcid":"https://orcid.org/0000-0002-6765-9462"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianbo Ma","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lei Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Zhu","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685741","display_name":"Jinke Li","orcid":"https://orcid.org/0000-0002-2974-1756"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinke Li","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013891900","display_name":"Dongdi Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongdi Zhao","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100773522","display_name":"Ming Liu","orcid":"https://orcid.org/0000-0001-8504-1335"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Liu","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057405217","display_name":"Feijun Jiang","orcid":"https://orcid.org/0000-0001-5579-5144"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feijun Jiang","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5163,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69204852,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"892","last_page":"899"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":0.9991000294685364,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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/keyword-spotting","display_name":"Keyword spotting","score":0.8710516691207886},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8451966047286987},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7353063821792603},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5956650376319885},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5906516909599304},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.48639753460884094},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47505828738212585},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4636669456958771},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.42299801111221313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40245521068573},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.14226379990577698},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09543755650520325}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8710516691207886},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8451966047286987},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7353063821792603},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5956650376319885},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5906516909599304},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.48639753460884094},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47505828738212585},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4636669456958771},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.42299801111221313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40245521068573},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.14226379990577698},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09543755650520325},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688326","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.5699999928474426,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1163332818","https://openalex.org/W1538131130","https://openalex.org/W1897240248","https://openalex.org/W1978414903","https://openalex.org/W2034940213","https://openalex.org/W2056986588","https://openalex.org/W2061074721","https://openalex.org/W2061191841","https://openalex.org/W2117678320","https://openalex.org/W2121973264","https://openalex.org/W2147665979","https://openalex.org/W2289394825","https://openalex.org/W2289731793","https://openalex.org/W2398042854","https://openalex.org/W2407277936","https://openalex.org/W2516857479","https://openalex.org/W2622203030","https://openalex.org/W2748659049","https://openalex.org/W2767071179","https://openalex.org/W2784052451","https://openalex.org/W2890489755","https://openalex.org/W2890992173","https://openalex.org/W2898711434","https://openalex.org/W3016218307","https://openalex.org/W3097878195","https://openalex.org/W3112742522","https://openalex.org/W6632100814","https://openalex.org/W6755202765","https://openalex.org/W6787533431"],"related_works":["https://openalex.org/W876328409","https://openalex.org/W4319068615","https://openalex.org/W4214946933","https://openalex.org/W1879255185","https://openalex.org/W2148473678","https://openalex.org/W2769861442","https://openalex.org/W2120442551","https://openalex.org/W1980506188","https://openalex.org/W2885833775","https://openalex.org/W2205176333"],"abstract_inverted_index":{"Conventional":[0],"keyword":[1],"spotting":[2],"(KWS)":[3],"systems":[4,19],"typically":[5],"use":[6],"microphone":[7],"array":[8],"techniques":[9],"to":[10,49,124],"improve":[11],"robustness":[12],"against":[13],"noise":[14],"and":[15],"reverberation.":[16],"However,":[17],"KWS":[18,51,59,70,82,91,99],"with":[20],"such":[21],"traditional":[22,98],"speech":[23,42,66],"enhancement":[24,43,67],"methods":[25],"may":[26],"not":[27,46,93],"always":[28],"yield":[29],"the":[30,37,41,50,58,69,80,87,97,108,116],"optimal":[31],"performance":[32],"in":[33],"different":[34],"conditions,":[35],"as":[36],"optimization":[38],"criterion":[39],"for":[40,65],"part":[44],"is":[45],"directly":[47],"relevant":[48],"objective.":[52],"In":[53],"this":[54],"work,":[55],"we":[56],"explore":[57],"system":[60,92,117],"by":[61,77,101,127],"encompassing":[62],"neural":[63,71,89],"beamforming":[64,90],"within":[68],"network,":[72],"which":[73,119],"updates":[74],"both":[75],"parameters":[76],"jointly":[78],"optimizing":[79],"unique":[81],"criteria.":[83],"We":[84],"demonstrate":[85],"that":[86],"proposed":[88],"only":[94],"significantly":[95],"outperforms":[96],"method":[100],"improving":[102],"30%":[103],"relative":[104],"recall":[105],"rate":[106],"at":[107],"same":[109],"precision,":[110],"but":[111],"also":[112],"can":[113],"obviously":[114],"reduce":[115],"complexity,":[118],"could":[120],"be":[121,125],"much":[122],"easier":[123],"adopted":[126],"small":[128],"resource":[129],"required":[130],"devices.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
