{"id":"https://openalex.org/W4392910572","doi":"https://doi.org/10.1109/icassp48485.2024.10447235","title":"Speech Guided Masked Image Modeling for Visually Grounded Speech","display_name":"Speech Guided Masked Image Modeling for Visually Grounded Speech","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910572","doi":"https://doi.org/10.1109/icassp48485.2024.10447235"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5101319314","display_name":"Jongbhin Woo","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jongbhin Woo","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014059162","display_name":"Hyeonggon Ryu","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeonggon Ryu","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070707693","display_name":"Arda Senocak","orcid":"https://orcid.org/0000-0001-9141-3270"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Arda Senocak","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101319314"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.7223,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68647408,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"8361","last_page":"8365"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.6773999929428101,"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"}},"topics":[{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.6773999929428101,"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/T12031","display_name":"Speech and dialogue systems","score":0.6610999703407288,"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":0.6262000203132629,"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":0.7111312747001648},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6179697513580322},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4521104395389557},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3998171389102936},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3441646099090576}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7111312747001648},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6179697513580322},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4521104395389557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3998171389102936},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3441646099090576}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.5199999809265137}],"awards":[{"id":"https://openalex.org/G1739134435","display_name":null,"funder_award_id":"IITP-","funder_id":"https://openalex.org/F4320324891","funder_display_name":"Iran Telecommunication Research Center"},{"id":"https://openalex.org/G2327342398","display_name":null,"funder_award_id":"RS-2023-0021","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G8670528041","display_name":null,"funder_award_id":"IITP-2024-RS-2023-00259991","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2556930864","https://openalex.org/W2586148577","https://openalex.org/W2842511635","https://openalex.org/W2938991416","https://openalex.org/W2962862718","https://openalex.org/W2963330681","https://openalex.org/W2963902314","https://openalex.org/W3035682985","https://openalex.org/W3099142230","https://openalex.org/W3159481202","https://openalex.org/W3174311593","https://openalex.org/W3196698946","https://openalex.org/W3197828817","https://openalex.org/W3200287550","https://openalex.org/W3209059054","https://openalex.org/W4224875474","https://openalex.org/W4297808394","https://openalex.org/W4313156423","https://openalex.org/W4319862477","https://openalex.org/W4372266917","https://openalex.org/W4385245566","https://openalex.org/W4386075997","https://openalex.org/W6729977899","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6770596778","https://openalex.org/W6784333009","https://openalex.org/W6844432065"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"objective":[1],"of":[2,11,63],"this":[3,49,53,97],"study":[4],"is":[5],"to":[6,32,109,144],"investigate":[7],"the":[8,61,80,94,101,107,111,118,129],"learning":[9,19,23,45,131],"process":[10],"Visually":[12],"Grounded":[13],"Speech":[14],"(VGS)":[15],"models":[16,30,84,146],"through":[17],"joint":[18],"that":[20,69,90,124,147],"combines":[21],"contrastive":[22,44,81,130],"and":[24,38,114],"masked":[25,88,112],"image":[26],"modeling.":[27],"Typically,":[28],"VGS":[29,83],"ahn":[31],"establish":[33],"audio-visual":[34,134],"alignment":[35],"between":[36,117],"images":[37],"then":[39],"spoken":[40,70,103],"captions":[41,71],"within":[42,128],"a":[43,87],"framework.":[46],"Building":[47],"upon":[48],"seminal":[50],"concept,":[51],"in":[52,93,100],"work,":[54],"we":[55,78],"explore":[56],"whether":[57],"visual":[58,73],"reconstruction":[59,127],"with":[60],"help":[62],"cross-modality":[64],"can":[65],"enhance":[66],"alignment,":[67],"given":[68],"describe":[72],"appearances.":[74],"To":[75],"achieve":[76],"this,":[77],"extend":[79],"learning-based":[82],"by":[85],"incorporating":[86],"autoencoder":[89],"utilizes":[91],"cross-attention":[92],"decoder.":[95],"Through":[96],"cross-modal":[98,126],"interaction":[99],"decoder,":[102],"caption":[104],"features":[105],"guide":[106],"model":[108],"reconstruct":[110],"patches":[113],"capture":[115],"correspondence":[116],"two":[119],"modalities.":[120],"Our":[121],"findings":[122],"suggest":[123],"integrating":[125],"framework":[132],"enhances":[133],"feature":[135],"alignment.":[136],"Consequently,":[137],"our":[138],"proposed":[139],"method":[140],"gives":[141],"comparable":[142],"performance":[143],"existing":[145],"utilize":[148],"prior":[149],"knowledge":[150],"or":[151,159],"other":[152],"modalities,":[153],"such":[154],"as":[155],"object":[156],"region":[157],"proposals":[158],"Contrastive":[160],"Language-Image":[161],"Pretraining":[162],"(CLIP).":[163]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}