{"id":"https://openalex.org/W4402352712","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650095","title":"Target Speech Extraction with Pre-trained AV-HuBERT and Mask-And-Recover Strategy","display_name":"Target Speech Extraction with Pre-trained AV-HuBERT and Mask-And-Recover Strategy","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352712","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650095"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5101759485","display_name":"Wenxuan Wu","orcid":"https://orcid.org/0000-0002-5371-1186"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wenxuan Wu","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108049724","display_name":"Xueyuan Chen","orcid":"https://orcid.org/0000-0003-0493-839X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xueyuan Chen","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xixin Wu","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/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":0.9993000030517578,"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":0.689041256904602},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5712140202522278},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5525121092796326},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43068695068359375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39698168635368347},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32549500465393066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.689041256904602},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5712140202522278},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5525121092796326},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43068695068359375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39698168635368347},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32549500465393066},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":44,"referenced_works":["https://openalex.org/W2092392156","https://openalex.org/W2141998673","https://openalex.org/W2734774145","https://openalex.org/W2741151796","https://openalex.org/W2802511083","https://openalex.org/W2808631503","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2964058413","https://openalex.org/W2972513594","https://openalex.org/W2973062255","https://openalex.org/W2990138404","https://openalex.org/W3008400075","https://openalex.org/W3016361963","https://openalex.org/W3024147341","https://openalex.org/W3097653961","https://openalex.org/W3099330747","https://openalex.org/W3103434036","https://openalex.org/W3163287738","https://openalex.org/W3182657421","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4205509257","https://openalex.org/W4214698081","https://openalex.org/W4224933800","https://openalex.org/W4225326644","https://openalex.org/W4281492411","https://openalex.org/W4294326507","https://openalex.org/W4295308317","https://openalex.org/W4319586244","https://openalex.org/W4367597591","https://openalex.org/W4372260307","https://openalex.org/W4372270069","https://openalex.org/W4372349800","https://openalex.org/W4375868968","https://openalex.org/W4375869294","https://openalex.org/W4375869413","https://openalex.org/W4385570757","https://openalex.org/W4385822391","https://openalex.org/W4385823134","https://openalex.org/W4392903361","https://openalex.org/W4392910324","https://openalex.org/W6780218876","https://openalex.org/W6810168380"],"related_works":["https://openalex.org/W2377297411","https://openalex.org/W3148217948","https://openalex.org/W2375788636","https://openalex.org/W2358561207","https://openalex.org/W2388704129","https://openalex.org/W2392827053","https://openalex.org/W2975617233","https://openalex.org/W3188962172","https://openalex.org/W2377877252","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Audio-visual":[0],"target":[1,132],"speech":[2,133],"extraction":[3],"(AV-TSE)":[4],"is":[5,23,147],"one":[6],"of":[7,18,21,115],"the":[8,19,32,58,81,101,110,122,143],"enabling":[9],"technologies":[10],"in":[11,31,113],"robotics":[12],"and":[13,83,117],"many":[14],"audiovisual":[15],"applications.":[16],"One":[17],"challenges":[20],"AV-TSE":[22,67],"how":[24],"to":[25,56,60,73],"effectively":[26],"utilize":[27],"audio-visual":[28],"synchronization":[29],"information":[30],"process.":[33],"AV-HuBERT":[34,64,124],"can":[35],"be":[36],"a":[37,62,89,137],"useful":[38],"pre-trained":[39,123],"model":[40,108,125],"for":[41,94,131],"lip-reading,":[42],"which":[43],"has":[44],"not":[45],"been":[46],"adopted":[47],"by":[48],"AV-TSE.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53,86,140],"would":[54],"like":[55],"explore":[57],"way":[59],"integrate":[61],"pretrained":[63],"into":[65],"our":[66,106],"system.":[68],"We":[69],"have":[70],"good":[71],"reasons":[72],"expect":[74],"an":[75],"improved":[76],"performance.":[77],"To":[78],"benefit":[79],"from":[80],"inter":[82],"intra-modality":[84],"correlations,":[85],"also":[87],"propose":[88],"novel":[90],"Mask-And-Recover":[91,145],"(MAR)":[92],"strategy":[93,146],"self-supervised":[95],"learning.":[96],"The":[97],"experimental":[98],"results":[99],"on":[100],"VoxCeleb2":[102],"dataset":[103],"show":[104],"that":[105,121,142],"proposed":[107,144],"outperforms":[109],"baselines":[111],"both":[112],"terms":[114],"subjective":[116],"objective":[118],"metrics,":[119],"suggesting":[120],"provides":[126],"more":[127],"informative":[128],"visual":[129],"cues":[130],"extraction.":[134],"Furthermore,":[135],"through":[136],"comparative":[138],"study,":[139],"confirm":[141],"significantly":[148],"effective.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}