{"id":"https://openalex.org/W4372270419","doi":"https://doi.org/10.1109/icassp49357.2023.10096858","title":"VE-KWS: Visual Modality Enhanced End-to-End Keyword Spotting","display_name":"VE-KWS: Visual Modality Enhanced End-to-End Keyword Spotting","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372270419","doi":"https://doi.org/10.1109/icassp49357.2023.10096858"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096858","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":"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/A5100437589","display_name":"Ao Zhang","orcid":"https://orcid.org/0000-0002-1536-2413"},"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":"Ao Zhang","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":"middle","author":{"id":"https://openalex.org/A5101808140","display_name":"Wang He","orcid":"https://orcid.org/0000-0002-3436-1299"},"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":"He Wang","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":"middle","author":{"id":"https://openalex.org/A5101783173","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0009-0001-2388-5935"},"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":"Pengcheng Guo","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":"middle","author":{"id":"https://openalex.org/A5010250251","display_name":"Yihui Fu","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":false,"raw_author_name":"Yihui Fu","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":"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":"middle","author":{"id":"https://openalex.org/A5068298033","display_name":"Yingying Gao","orcid":"https://orcid.org/0000-0002-6869-3013"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingying Gao","raw_affiliation_strings":["China Mobile Research Institute,Beijing,China","China Mobile Research Institute, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Beijing,China","institution_ids":["https://openalex.org/I180662265"]},{"raw_affiliation_string":"China Mobile Research Institute, Beijing, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618830","display_name":"Shilei Zhang","orcid":"https://orcid.org/0009-0007-5182-3065"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilei Zhang","raw_affiliation_strings":["China Mobile Research Institute,Beijing,China","China Mobile Research Institute, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Beijing,China","institution_ids":["https://openalex.org/I180662265"]},{"raw_affiliation_string":"China Mobile Research Institute, Beijing, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079750750","display_name":"Junlan Feng","orcid":"https://orcid.org/0000-0001-5292-2945"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlan Feng","raw_affiliation_strings":["China Mobile Research Institute,Beijing,China","China Mobile Research Institute, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Beijing,China","institution_ids":["https://openalex.org/I180662265"]},{"raw_affiliation_string":"China Mobile Research Institute, Beijing, China","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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":0.9586620330810547},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.8473026752471924},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.79538893699646},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7757498025894165},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7307592034339905},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5981320142745972},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5532914996147156},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5051954388618469},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4688834846019745},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4363630712032318},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4252541661262512},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41838568449020386}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9586620330810547},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.8473026752471924},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79538893699646},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7757498025894165},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7307592034339905},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5981320142745972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5532914996147156},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5051954388618469},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4688834846019745},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4363630712032318},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4252541661262512},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41838568449020386},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096858","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":26,"referenced_works":["https://openalex.org/W2034940213","https://openalex.org/W2170653751","https://openalex.org/W2897492880","https://openalex.org/W2900893004","https://openalex.org/W2937769560","https://openalex.org/W2963616706","https://openalex.org/W2963820951","https://openalex.org/W2972693890","https://openalex.org/W2972802573","https://openalex.org/W2973000846","https://openalex.org/W3016238098","https://openalex.org/W3024464021","https://openalex.org/W3095212293","https://openalex.org/W3097878195","https://openalex.org/W3107298252","https://openalex.org/W3161480375","https://openalex.org/W3163237592","https://openalex.org/W4221139382","https://openalex.org/W4224213421","https://openalex.org/W4224933780","https://openalex.org/W4224940398","https://openalex.org/W4226046733","https://openalex.org/W4297841230","https://openalex.org/W6739901393","https://openalex.org/W6771611251","https://openalex.org/W6782374147"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W73545470","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660"],"abstract_inverted_index":{"The":[0,92,140],"performance":[1,194],"of":[2,56,60,112,159],"the":[3,23,52,62,97,103,110,118,125,130,151,156,164,186,197,201],"keyword":[4,31],"spotting":[5],"(KWS)":[6],"system":[7],"based":[8],"on":[9,50,163,185],"audio":[10,85,114,122],"modality,":[11],"commonly":[12],"measured":[13],"in":[14,106,190,200],"false":[15,18,176,182],"alarms":[16],"and":[17,26,86,154,179],"rejects,":[19],"degrades":[20],"significantly":[21,138],"under":[22],"far":[24,131],"field":[25,132],"noisy":[27,134],"conditions.":[28],"Therefore,":[29],"audio-visual":[30],"spotting,":[32],"which":[33,83],"leverages":[34],"complementary":[35],"relationships":[36,64,153],"over":[37],"multiple":[38],"modalities,":[39,58],"has":[40],"recently":[41],"gained":[42],"much":[43],"attention.":[44],"However,":[45],"current":[46],"studies":[47],"mainly":[48],"focus":[49],"combining":[51],"exclusively":[53],"learned":[54],"representations":[55],"different":[57,147],"instead":[59],"exploring":[61],"modal":[63],"during":[65],"each":[66,160],"respective":[67],"modeling.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72],"propose":[73],"a":[74,174,180,191],"novel":[75],"visual":[76,87],"modality":[77],"enhanced":[78],"end-to-end":[79],"KWS":[80],"framework":[81],"(VE-KWS),":[82],"fuses":[84],"modalities":[88,148],"from":[89,102],"two":[90],"aspects.":[91],"first":[93],"one":[94,142],"is":[95,143],"utilizing":[96],"speaker":[98],"location":[99],"information":[100],"obtained":[101],"lip":[104],"region":[105],"videos":[107],"to":[108,149],"assist":[109],"training":[111],"multi-channel":[113],"beamformer.":[115],"By":[116],"involving":[117],"beamformer":[119],"as":[120],"an":[121],"enhancement":[123],"module,":[124],"acoustic":[126],"distortions,":[127],"caused":[128],"by":[129],"or":[133],"environments,":[135],"could":[136],"be":[137],"suppressed.":[139],"other":[141],"conducting":[144],"cross-attention":[145],"between":[146],"capture":[150],"inter-modal":[152],"help":[155],"representation":[157],"learning":[158],"modality.":[161],"Experiments":[162],"MSIP":[165],"challenge":[166],"corpus":[167],"show":[168],"that":[169],"our":[170],"proposed":[171],"model":[172],"achieves":[173],"2.79%":[175],"rejection":[177],"rate":[178,184],"2.95%":[181],"alarm":[183],"Eval":[187],"set,":[188],"resulting":[189],"new":[192],"SOTA":[193],"compared":[195],"with":[196],"top-ranking":[198],"systems":[199],"ICASSP2022":[202],"MISP":[203],"challenge.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}