{"id":"https://openalex.org/W4221141391","doi":"https://doi.org/10.1109/icassp43922.2022.9746360","title":"A Study of Designing Compact Audio-Visual Wake Word Spotting System Based on Iterative Fine-Tuning in Neural Network Pruning","display_name":"A Study of Designing Compact Audio-Visual Wake Word Spotting System Based on Iterative Fine-Tuning in Neural Network Pruning","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221141391","doi":"https://doi.org/10.1109/icassp43922.2022.9746360"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746360","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5103235094","display_name":"Hengshun Zhou","orcid":"https://orcid.org/0000-0001-7878-6531"},"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":true,"raw_author_name":"Hengshun Zhou","raw_affiliation_strings":["University of Science and Technology of China,Hefei,P. R. China","University of Science and Technology of China, Hefei, P. R. China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412670","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2410-2429"},"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":["University of Science and Technology of China,Hefei,P. R. China","University of Science and Technology of China, Hefei, P. R. China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020376803","display_name":"Chao-Han Huck Yang","orcid":"https://orcid.org/0000-0003-2879-8811"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao-Han Huck Yang","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA,USA","Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021081307","display_name":"Shifu Xiong","orcid":"https://orcid.org/0000-0003-4759-147X"},"institutions":[{"id":"https://openalex.org/I39774598","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64","country_code":"CN","type":"education","lineage":["https://openalex.org/I39774598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shifu Xiong","raw_affiliation_strings":["iFlytek Research,Hefei,P. R. China","iFlytek Research, Hefei, P. R. China"],"affiliations":[{"raw_affiliation_string":"iFlytek Research,Hefei,P. R. China","institution_ids":["https://openalex.org/I39774598"]},{"raw_affiliation_string":"iFlytek Research, Hefei, P. R. China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA,USA","Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103235094"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.6114,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.6331864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7572","last_page":"7576"},"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9940000176429749,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.820676863193512},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.6023210883140564},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5800296068191528},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5583488345146179},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5199938416481018},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.42824625968933105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36733126640319824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.820676863193512},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.6023210883140564},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5800296068191528},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5583488345146179},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5199938416481018},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.42824625968933105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36733126640319824},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746360","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2034940213","https://openalex.org/W2122797512","https://openalex.org/W2407023693","https://openalex.org/W2805003733","https://openalex.org/W2896422817","https://openalex.org/W2937769560","https://openalex.org/W2938873567","https://openalex.org/W2939412000","https://openalex.org/W2953219395","https://openalex.org/W2963163009","https://openalex.org/W2964187693","https://openalex.org/W2995816250","https://openalex.org/W3012505451","https://openalex.org/W3015118013","https://openalex.org/W3015287265","https://openalex.org/W3016218307","https://openalex.org/W3019293601","https://openalex.org/W3025581723","https://openalex.org/W3082089446","https://openalex.org/W3095012737","https://openalex.org/W3095694146","https://openalex.org/W3096662840","https://openalex.org/W3096976027","https://openalex.org/W3160521245","https://openalex.org/W3163074978","https://openalex.org/W3163237592","https://openalex.org/W3176579201","https://openalex.org/W3202528415","https://openalex.org/W4287101262","https://openalex.org/W4302028573","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6751979845","https://openalex.org/W6755691404","https://openalex.org/W6772029579","https://openalex.org/W6773423997","https://openalex.org/W6776291226","https://openalex.org/W6782374147","https://openalex.org/W6792494334","https://openalex.org/W6798258902"],"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":{"Audio-only":[0],"based":[1,75],"wake":[2],"word":[3],"spotting":[4],"(WWS)":[5],"is":[6],"challenging":[7],"under":[8,146],"noisy":[9,148],"conditions":[10],"due":[11],"to":[12,36,43,53,111,168],"the":[13,33,38,50,66,72,90,101,112,131,140,156,174],"environmental":[14],"interference":[15],"in":[16,41,105,126],"signal":[17],"transmission.":[18],"In":[19],"this":[20],"paper,":[21],"we":[22,47,93],"investigate":[23],"on":[24,76,119],"designing":[25],"a":[26,80,84,95,127,169],"compact":[27],"audio-visual":[28,73,124],"WWS":[29,125,165],"system":[30,134,145],"by":[31,65],"utilizing":[32],"visual":[34,45],"information":[35],"alleviate":[37],"degradation.":[39],"Specifically,":[40],"order":[42],"use":[44],"information,":[46],"first":[48],"encode":[49],"detected":[51],"lips":[52],"fixed-size":[54],"vectors":[55],"with":[56,61,161],"MobileNet":[57],"and":[58,83,114,159],"concatenate":[59],"them":[60],"acoustic":[62],"features":[63],"followed":[64],"fusion":[67],"network":[68,78,97,157],"for":[69,123,173],"WWS.":[70],"However,":[71],"model":[74],"neural":[77,96],"requires":[79],"large":[81],"footprint":[82],"high":[85],"computational":[86],"complexity.":[87],"To":[88],"meet":[89],"application":[91],"requirements,":[92],"introduce":[94],"pruning":[98,152],"strategy":[99],"via":[100],"lottery":[102],"ticket":[103],"hypothesis":[104],"an":[106],"iterative":[107],"fine-tuning":[108],"manner":[109],"(LTH-IF),":[110],"single-modal":[113],"multi-modal":[115],"models,":[116],"respectively.":[117],"Tested":[118],"our":[120],"in-house":[121],"corpus":[122],"home":[128],"TV":[129,175],"scene,":[130],"proposed":[132],"audiovisual":[133],"achieves":[135],"significant":[136],"performance":[137],"improvements":[138],"over":[139],"single-modality":[141],"(audio-only":[142],"or":[143],"video-only)":[144],"different":[147],"conditions.":[149],"Moreover,":[150],"LTH-IF":[151],"can":[153],"largely":[154],"reduce":[155],"parameters":[158],"computations":[160],"no":[162],"degradation":[163],"of":[164],"performance,":[166],"leading":[167],"potential":[170],"product":[171],"solution":[172],"wake-up":[176],"scenario.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}