{"id":"https://openalex.org/W4407449647","doi":"https://doi.org/10.1109/tcsvt.2025.3541788","title":"Lightweight Audio-Visual Wake Word Spotting With Diverse Acoustic Knowledge Distillation","display_name":"Lightweight Audio-Visual Wake Word Spotting With Diverse Acoustic Knowledge Distillation","publication_year":2025,"publication_date":"2025-02-13","ids":{"openalex":"https://openalex.org/W4407449647","doi":"https://doi.org/10.1109/tcsvt.2025.3541788"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3541788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3541788","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-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":null,"display_name":"Ke-Wei Li","orcid":"https://orcid.org/0009-0006-4315-2874"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke-Wei Li","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, P. R. China"],"raw_orcid":"https://orcid.org/0009-0006-4315-2874","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106443644","display_name":"Hang Chen","orcid":"https://orcid.org/0000-0002-8364-4762"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Chen","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-2387-0389","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103235094","display_name":"Hengshun Zhou","orcid":"https://orcid.org/0000-0001-7878-6531"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heng-Shun Zhou","raw_affiliation_strings":["iFlytek Research, Hefei, Anhui, China","iFlytek Research, Hefei, Anhui, P.R.China"],"raw_orcid":"https://orcid.org/0000-0001-7878-6531","affiliations":[{"raw_affiliation_string":"iFlytek Research, Hefei, Anhui, China","institution_ids":[]},{"raw_affiliation_string":"iFlytek Research, Hefei, Anhui, P.R.China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":["Computer Engineering Department, University of Palermo, Palermo, Italy","FULL Professor at the University of Palermo, Italy"],"raw_orcid":"https://orcid.org/0000-0002-0770-0507","affiliations":[{"raw_affiliation_string":"Computer Engineering Department, University of Palermo, Palermo, Italy","institution_ids":["https://openalex.org/I900890020"]},{"raw_affiliation_string":"FULL Professor at the University of Palermo, Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064699619","display_name":"Shutong Niu","orcid":"https://orcid.org/0000-0003-0315-1042"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu-Tong Niu","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, P. R. China"],"raw_orcid":"https://orcid.org/0000-0003-0315-1042","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":null,"display_name":"Shi-Fu Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi-Fu Xiong","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8049,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.81855514,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"35","issue":"7","first_page":"7308","last_page":"7320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"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":0.9980999827384949,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9861999750137329,"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/spotting","display_name":"Spotting","score":0.9349526166915894},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7251005172729492},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6182147264480591},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5284067392349243},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5200409889221191},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42136043310165405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4202573001384735},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4179689586162567},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.19981956481933594},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10796359181404114}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.9349526166915894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7251005172729492},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6182147264480591},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5284067392349243},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5200409889221191},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42136043310165405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4202573001384735},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4179689586162567},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.19981956481933594},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10796359181404114},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2025.3541788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3541788","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:iris.unipa.it:10447/674965","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/674965","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1713836045","display_name":null,"funder_award_id":"62171427","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W753847829","https://openalex.org/W1553469512","https://openalex.org/W1987454298","https://openalex.org/W1999121090","https://openalex.org/W2015394094","https://openalex.org/W2034940213","https://openalex.org/W2122797512","https://openalex.org/W2127141656","https://openalex.org/W2142384583","https://openalex.org/W2148154194","https://openalex.org/W2148613904","https://openalex.org/W2285716245","https://openalex.org/W2294370754","https://openalex.org/W2463402750","https://openalex.org/W2508907749","https://openalex.org/W2558258029","https://openalex.org/W2587529061","https://openalex.org/W2748659049","https://openalex.org/W2752782242","https://openalex.org/W2799062425","https://openalex.org/W2887783173","https://openalex.org/W2889839708","https://openalex.org/W2953219395","https://openalex.org/W2963881567","https://openalex.org/W2965076062","https://openalex.org/W2969985801","https://openalex.org/W2971047694","https://openalex.org/W2972775954","https://openalex.org/W2981694290","https://openalex.org/W3007947150","https://openalex.org/W3016218307","https://openalex.org/W3034368386","https://openalex.org/W3081434152","https://openalex.org/W3128533107","https://openalex.org/W3130394099","https://openalex.org/W3144653585","https://openalex.org/W3163237592","https://openalex.org/W3165695488","https://openalex.org/W3168662520","https://openalex.org/W3197089327","https://openalex.org/W3199053851","https://openalex.org/W4224213421","https://openalex.org/W4224933780","https://openalex.org/W4224940398","https://openalex.org/W4226046733","https://openalex.org/W4289752563","https://openalex.org/W4297841644","https://openalex.org/W4309660795","https://openalex.org/W4319996358","https://openalex.org/W4372270419","https://openalex.org/W4375869136","https://openalex.org/W4385822513","https://openalex.org/W4385823066","https://openalex.org/W4385975752","https://openalex.org/W4386057728","https://openalex.org/W4389987369","https://openalex.org/W4390659080","https://openalex.org/W4399474077","https://openalex.org/W4400188641","https://openalex.org/W4402892179","https://openalex.org/W4403386295","https://openalex.org/W4403791995","https://openalex.org/W6638523607","https://openalex.org/W6679909955","https://openalex.org/W6697633650","https://openalex.org/W6758731277","https://openalex.org/W6780218876","https://openalex.org/W6791742336","https://openalex.org/W6796538260","https://openalex.org/W6810280441"],"related_works":["https://openalex.org/W2034439647","https://openalex.org/W3184921334","https://openalex.org/W4249589822","https://openalex.org/W4386895402","https://openalex.org/W2103063669","https://openalex.org/W4380551034","https://openalex.org/W3202382261","https://openalex.org/W2028814537","https://openalex.org/W2058491579","https://openalex.org/W1483316057"],"abstract_inverted_index":{"Audio-Visual":[0],"Wake":[1],"Word":[2],"Spotting":[3],"(AVWWS)":[4],"aims":[5],"to":[6,71,81,91,196,204],"accurately":[7],"detect":[8],"user-defined":[9],"keywords":[10],"by":[11],"leveraging":[12],"the":[13,28,40,44,83,89,92,99,121,150,205,222,225],"complementary":[14],"nature":[15],"of":[16,30,46,88,114,211],"different":[17],"modalities":[18],"in":[19,33],"challenging":[20],"acoustic":[21,59,199],"environments.":[22],"However,":[23],"two":[24,73],"primary":[25],"challenges":[26],"hinder":[27],"application":[29],"AVWWS":[31],"models":[32,75,179],"real-world":[34],"scenarios:":[35],"increased":[36],"model":[37,118,141],"parameters":[38],"involving":[39],"video":[41],"modality":[42],"and":[43,76,85,107,133,145,158,164,177,189,192,201,224],"scarcity":[45],"paired":[47,190],"audio-visual":[48,93,116,206],"data.":[49,109],"To":[50],"address":[51],"these":[52],"issues,":[53],"we":[54],"propose":[55],"a":[56,128,134,154],"novel":[57],"diverse":[58],"knowledge":[60,79],"distillation":[61,80],"(DAKD)":[62],"framework,":[63],"which":[64],"utilizes":[65],"easily":[66],"accessible":[67],"single-modality":[68],"audio":[69],"data":[70],"train":[72],"teacher":[74,130,136],"employs":[77],"cross-modal":[78],"transfer":[82],"generalization":[84],"de-noising":[86,135,202],"capabilities":[87,203],"teachers":[90],"student":[94,117,207],"model.":[95,138,208],"This":[96],"approach":[97],"mitigates":[98],"overfitting":[100],"risk":[101],"associated":[102],"with":[103,171,234],"large":[104],"parameter":[105,173],"counts":[106],"limited":[108],"The":[110,139,175,209],"DAKD":[111,214],"framework":[112,215],"consists":[113],"an":[115],"based":[119,148],"on":[120,149,221],"lightweight":[122],"multi-scale":[123,160],"temporal-spatial":[124,169],"attention":[125,156],"(LMTSA)":[126],"architecture,":[127],"multi-conditional":[129],"(MCT)":[131],"model,":[132],"(DNT)":[137],"LMTSA":[140],"integrates":[142],"compact":[143],"3D":[144],"2D":[146],"blocks":[147],"ResNet":[151],"architecture":[152],"through":[153,218],"simple":[155],"module":[157],"accepts":[159],"supervision":[161],"from":[162],"word-level":[163],"phone-level":[165],"labels,":[166],"achieving":[167],"joint":[168],"modeling":[170],"minimal":[172],"usage.":[174],"MCT":[176],"DNT":[178],"were":[180],"trained":[181],"using":[182],"extensive":[183],"real":[184],"or":[185],"simulated":[186],"far-field":[187,193],"speech":[188],"near-field":[191],"speech,":[194],"respectively,":[195],"generalize":[197],"unseen":[198],"environments":[200],"effectiveness":[210],"our":[212],"proposed":[213],"is":[216],"validated":[217],"comprehensive":[219],"experiments":[220],"MISP2021":[223,227],"updated":[226],"Eval":[228],"Hard":[229],"datasets,":[230],"establishing":[231],"new":[232],"benchmarks":[233],"fewer":[235],"parameters.":[236],"Our":[237],"code":[238],"will":[239],"be":[240],"available":[241],"at":[242],"<uri":[243],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[244],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/wikkk-tp/AVWWS_DAKD</uri>.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-02-14T00:00:00"}