{"id":"https://openalex.org/W4392450191","doi":"https://doi.org/10.1109/tvcg.2024.3372092","title":"Robust Dual-Modal Speech Keyword Spotting for XR Headsets","display_name":"Robust Dual-Modal Speech Keyword Spotting for XR Headsets","publication_year":2024,"publication_date":"2024-03-05","ids":{"openalex":"https://openalex.org/W4392450191","doi":"https://doi.org/10.1109/tvcg.2024.3372092","pmid":"https://pubmed.ncbi.nlm.nih.gov/38437114"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2024.3372092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2024.3372092","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5054435697","display_name":"Zhuojiang Cai","orcid":"https://orcid.org/0009-0005-3404-118X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhuojiang Cai","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072129728","display_name":"Yuhan Ma","orcid":"https://orcid.org/0009-0008-4679-0454"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhan Ma","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050527785","display_name":"Feng Lu","orcid":"https://orcid.org/0000-0001-9064-7964"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Lu","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5054435697"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":1.3901,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82925463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"30","issue":"5","first_page":"2507","last_page":"2516"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9980999827384949,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9855999946594238,"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":0.8455156087875366},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.7483826279640198},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.6881608963012695},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.608599066734314},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5712747573852539},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5131271481513977},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4204222857952118},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38582655787467957},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33751776814460754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8455156087875366},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.7483826279640198},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6881608963012695},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.608599066734314},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5712747573852539},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5131271481513977},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4204222857952118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38582655787467957},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33751776814460754},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009068","descriptor_name":"Movement","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009068","descriptor_name":"Movement","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009068","descriptor_name":"Movement","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tvcg.2024.3372092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2024.3372092","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},{"id":"pmid:38437114","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38437114","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on visualization and computer graphics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1485222997","https://openalex.org/W1904948456","https://openalex.org/W1999121090","https://openalex.org/W2006071649","https://openalex.org/W2025530819","https://openalex.org/W2034940213","https://openalex.org/W2056986588","https://openalex.org/W2057959448","https://openalex.org/W2096391593","https://openalex.org/W2122797512","https://openalex.org/W2125490883","https://openalex.org/W2148154194","https://openalex.org/W2170151952","https://openalex.org/W2407023693","https://openalex.org/W2510945575","https://openalex.org/W2587529061","https://openalex.org/W2697044473","https://openalex.org/W2743686029","https://openalex.org/W2783652918","https://openalex.org/W2783985400","https://openalex.org/W2789252873","https://openalex.org/W2793257307","https://openalex.org/W2797583228","https://openalex.org/W2802223794","https://openalex.org/W2889182547","https://openalex.org/W2889384527","https://openalex.org/W2889839708","https://openalex.org/W2901907199","https://openalex.org/W2921295135","https://openalex.org/W2941048526","https://openalex.org/W2963030892","https://openalex.org/W2964187693","https://openalex.org/W2973226577","https://openalex.org/W3019293601","https://openalex.org/W3040975780","https://openalex.org/W3083703874","https://openalex.org/W3091762102","https://openalex.org/W3093564344","https://openalex.org/W3098773154","https://openalex.org/W3119913666","https://openalex.org/W3136429823","https://openalex.org/W3160728073","https://openalex.org/W3176579201","https://openalex.org/W3182888500","https://openalex.org/W3196496149","https://openalex.org/W3198035615","https://openalex.org/W3199591511","https://openalex.org/W3202693387","https://openalex.org/W4200482297","https://openalex.org/W4206567542","https://openalex.org/W4224287316","https://openalex.org/W4232282348","https://openalex.org/W4282916028","https://openalex.org/W4284884132","https://openalex.org/W4294691842","https://openalex.org/W4297841641","https://openalex.org/W4366547682","https://openalex.org/W4367662679","https://openalex.org/W6750665317"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W3119978414","https://openalex.org/W4286904253","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2117995638"],"abstract_inverted_index":{"While":[0],"speech":[1,14],"interaction":[2],"finds":[3],"widespread":[4],"utility":[5],"within":[6],"the":[7,52,87,129],"Extended":[8],"Reality":[9],"(XR)":[10],"domain,":[11],"conventional":[12],"vocal":[13],"keyword":[15,68],"spotting":[16,69],"systems":[17],"continue":[18],"to":[19,37,85],"grapple":[20],"with":[21],"formidable":[22],"challenges,":[23,45],"including":[24],"suboptimal":[25],"performance":[26,89],"in":[27,31,110,119,131],"noisy":[28,114],"environments,":[29,115],"impracticality":[30],"situations":[32],"requiring":[33],"silence,":[34],"and":[35,57,82,113],"susceptibility":[36],"inadvertent":[38],"activations":[39],"when":[40],"others":[41],"speak":[42],"nearby.":[43],"These":[44],"however,":[46],"can":[47],"potentially":[48],"be":[49],"surmounted":[50],"through":[51],"cost-effective":[53],"fusion":[54,80],"of":[55],"voice":[56],"lip":[58],"movement":[59],"information.":[60],"Consequently,":[61],"we":[62,125],"propose":[63],"a":[64],"novel":[65],"vocal-echoic":[66],"dual-modal":[67,98],"system":[70,99,130],"designed":[71],"for":[72],"XR":[73],"headsets.":[74],"We":[75],"devise":[76],"two":[77],"different":[78],"modal":[79],"approches":[81],"conduct":[83],"experiments":[84],"test":[86],"system's":[88],"across":[90],"diverse":[91],"scenarios.":[92],"The":[93,137],"results":[94],"show":[95],"that":[96],"our":[97],"not":[100],"only":[101],"consistently":[102],"outperforms":[103],"its":[104],"single-modal":[105],"counterparts,":[106],"demonstrating":[107],"higher":[108],"precision":[109],"both":[111],"typical":[112],"but":[116],"also":[117],"excels":[118],"accurately":[120],"identifying":[121],"silent":[122],"utterances.":[123],"Furthermore,":[124],"have":[126],"successfully":[127],"applied":[128],"real-time":[132],"demonstrations,":[133],"achieving":[134],"promising":[135],"results.":[136],"code":[138],"is":[139],"available":[140],"at":[141],"https://github.com/caizhuojiang/VE-KWS.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
