{"id":"https://openalex.org/W4319862239","doi":"https://doi.org/10.1109/slt54892.2023.10023254","title":"Speed-Robust Keyword Spotting Via Soft Self-Attention on Multi-Scale Features","display_name":"Speed-Robust Keyword Spotting Via Soft Self-Attention on Multi-Scale Features","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862239","doi":"https://doi.org/10.1109/slt54892.2023.10023254"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023254","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5032101339","display_name":"Chaoyue Ding","orcid":"https://orcid.org/0009-0000-0161-4838"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chaoyue Ding","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060389661","display_name":"Jiakui Li","orcid":"https://orcid.org/0000-0002-6065-6648"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiakui Li","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091168107","display_name":"Martin Zong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Zong","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003607066","display_name":"Baoxiang Li","orcid":"https://orcid.org/0009-0009-4490-2157"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baoxiang Li","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0889,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77743917,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1104","last_page":"1111"},"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/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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/T10860","display_name":"Speech and Audio Processing","score":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.8675154447555542},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6998385190963745},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.6457142233848572},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6001764535903931},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5594247579574585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49318522214889526},{"id":"https://openalex.org/keywords/frame-rate","display_name":"Frame rate","score":0.4580298066139221},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4277638792991638},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4155625104904175},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.098971426486969}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8675154447555542},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6998385190963745},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.6457142233848572},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6001764535903931},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5594247579574585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49318522214889526},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.4580298066139221},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4277638792991638},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4155625104904175},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.098971426486969},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023254","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1544266773","https://openalex.org/W1734538896","https://openalex.org/W2034940213","https://openalex.org/W2056986588","https://openalex.org/W2407023693","https://openalex.org/W2526425061","https://openalex.org/W2587529061","https://openalex.org/W2622203030","https://openalex.org/W2697044473","https://openalex.org/W2748659049","https://openalex.org/W2752782242","https://openalex.org/W2766219058","https://openalex.org/W2769912137","https://openalex.org/W2809099079","https://openalex.org/W2892300106","https://openalex.org/W2936774411","https://openalex.org/W2938873567","https://openalex.org/W2953219395","https://openalex.org/W2962780374","https://openalex.org/W2962959915","https://openalex.org/W2963414149","https://openalex.org/W2963628261","https://openalex.org/W2963840672","https://openalex.org/W2964187693","https://openalex.org/W2973226577","https://openalex.org/W3016218307","https://openalex.org/W3016238098","https://openalex.org/W3019293601","https://openalex.org/W3098773154","https://openalex.org/W3133600743","https://openalex.org/W3148564648","https://openalex.org/W3154934206","https://openalex.org/W3196509839","https://openalex.org/W3196778512","https://openalex.org/W3198035615","https://openalex.org/W4224916413","https://openalex.org/W6631190155","https://openalex.org/W6632425017","https://openalex.org/W6696085341","https://openalex.org/W6746451879","https://openalex.org/W6790834777","https://openalex.org/W6800443949"],"related_works":["https://openalex.org/W2114097550","https://openalex.org/W4385352507","https://openalex.org/W2918559346","https://openalex.org/W84309476","https://openalex.org/W4389912005","https://openalex.org/W4286904253","https://openalex.org/W2386245264","https://openalex.org/W2388033618","https://openalex.org/W2378448517","https://openalex.org/W2017737780"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,21,86],"focus":[4],"on":[5,114,139],"the":[6,63,69,111,128],"robustness":[7],"of":[8,68,82,121],"keyword":[9],"spotting":[10],"(KWS)":[11],"at":[12],"various":[13],"speech":[14,44,71,94],"speeds.":[15],"First,":[16],"to":[17,32,39,43,54,65,74],"enable":[18],"small-footprint":[19],"KWS,":[20],"graft":[22],"a":[23,28,46,118,140,144],"depthwise":[24],"separable":[25],"convolution":[26,31],"and":[27,73,99,124,143],"dilated":[29],"temporal":[30],"build":[33],"our":[34,61,108,133],"basic":[35],"model":[36,62,102,109,122,134],"block.":[37],"Second,":[38],"make":[40],"KWS":[41],"desensitized":[42],"rate,":[45],"simple":[47],"yet":[48],"effective":[49],"soft":[50],"self-attention":[51],"is":[52],"proposed":[53],"operate":[55],"between":[56],"different":[57],"hierarchical":[58],"features,":[59],"offering":[60],"ability":[64],"be":[66],"aware":[67],"speaker's":[70],"rate":[72],"dynamically":[75],"integrate":[76],"multi-scale":[77],"features":[78],"from":[79],"varying":[80],"sizes":[81],"receptive":[83],"fields.":[84],"Besides,":[85],"construct":[87],"two":[88],"frame-level":[89],"annotated":[90],"Chinese":[91],"intelligent":[92],"in-car":[93],"commands":[95],"datasets,":[96],"termed":[97],"Car-C1":[98],"Car-C2,":[100],"for":[101],"evaluation.":[103],"Experimental":[104],"results":[105],"show":[106],"that":[107,132],"achieves":[110],"highest":[112],"accuracy":[113],"both":[115],"datasets":[116],"with":[117],"comparable":[119],"number":[120],"parameters":[123],"computational":[125],"cost.":[126],"Meanwhile,":[127],"sensitivity":[129],"analysis":[130],"suggests":[131],"outperforms":[135],"baselines":[136],"when":[137],"tested":[138],"fast":[141],"corpus":[142],"slow":[145],"corpus.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}