{"id":"https://openalex.org/W4403936871","doi":"https://doi.org/10.1109/lwc.2024.3488859","title":"Multimodal Semantic Communication for Generative Audio-Driven Video Conferencing","display_name":"Multimodal Semantic Communication for Generative Audio-Driven Video Conferencing","publication_year":2024,"publication_date":"2024-10-31","ids":{"openalex":"https://openalex.org/W4403936871","doi":"https://doi.org/10.1109/lwc.2024.3488859"},"language":"en","primary_location":{"id":"doi:10.1109/lwc.2024.3488859","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lwc.2024.3488859","pdf_url":null,"source":{"id":"https://openalex.org/S2500830676","display_name":"IEEE Wireless Communications Letters","issn_l":"2162-2337","issn":["2162-2337","2162-2345"],"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 Wireless Communications Letters","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":"https://openalex.org/A5071788075","display_name":"Haonan Tong","orcid":"https://orcid.org/0000-0002-1835-4769"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haonan Tong","raw_affiliation_strings":["Beijing Key Laboratory of Network System Architecture and Convergence and the Beijing Advanced Information Network Laboratory, Beijing University of Posts and Telecommunications, Beijing, China","Beijing Key Laboratory of Network System Architecture and Convergence, China"],"raw_orcid":"https://orcid.org/0000-0002-1835-4769","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Network System Architecture and Convergence and the Beijing Advanced Information Network Laboratory, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing Key Laboratory of Network System Architecture and Convergence, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101639297","display_name":"Haopeng Li","orcid":"https://orcid.org/0000-0001-8175-5381"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haopeng Li","raw_affiliation_strings":["Beijing Key Laboratory of Network System Architecture and Convergence and the Beijing Advanced Information Network Laboratory, Beijing University of Posts and Telecommunications, Beijing, China","Beijing Key Laboratory of Network System Architecture and Convergence, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Network System Architecture and Convergence and the Beijing Advanced Information Network Laboratory, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing Key Laboratory of Network System Architecture and Convergence, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068782412","display_name":"Hongyang Du","orcid":"https://orcid.org/0000-0002-8220-6525"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hongyang Du","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, University of Hong Kong, Hong Kong, SAR, China","Department of Electrical and Electronic Engineering, University of Hong Kong, Pok Fu Lam, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-8220-6525","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, University of Hong Kong, Pok Fu Lam, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066878475","display_name":"Zhaohui Yang","orcid":"https://orcid.org/0000-0002-4475-589X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaohui Yang","raw_affiliation_strings":["College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-4475-589X","affiliations":[{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009078493","display_name":"Changchuan Yin","orcid":"https://orcid.org/0000-0001-8969-1431"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changchuan Yin","raw_affiliation_strings":["Beijing Key Laboratory of Network System Architecture and Convergence and the Beijing Advanced Information Network Laboratory, Beijing University of Posts and Telecommunications, Beijing, China","Beijing Key Laboratory of Network System Architecture and Convergence, China"],"raw_orcid":"https://orcid.org/0000-0001-8969-1431","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Network System Architecture and Convergence and the Beijing Advanced Information Network Laboratory, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing Key Laboratory of Network System Architecture and Convergence, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091266202","display_name":"Dusit Niyato","orcid":"https://orcid.org/0000-0002-7442-7416"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dusit Niyato","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore","College of Computing and Data Science, Nanyang Technological University (NTU), Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7442-7416","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3601,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93334905,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"14","issue":"1","first_page":"93","last_page":"97"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9751999974250793,"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/T12031","display_name":"Speech and dialogue systems","score":0.9751999974250793,"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/computer-science","display_name":"Computer science","score":0.8171088695526123},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.5867651700973511},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5409702658653259},{"id":"https://openalex.org/keywords/videoconferencing","display_name":"Videoconferencing","score":0.5343090295791626},{"id":"https://openalex.org/keywords/teleconference","display_name":"Teleconference","score":0.4194491505622864},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3943633437156677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2916378974914551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8171088695526123},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5867651700973511},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5409702658653259},{"id":"https://openalex.org/C22561748","wikidata":"https://www.wikidata.org/wiki/Q854954","display_name":"Videoconferencing","level":2,"score":0.5343090295791626},{"id":"https://openalex.org/C126669455","wikidata":"https://www.wikidata.org/wiki/Q1630941","display_name":"Teleconference","level":2,"score":0.4194491505622864},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3943633437156677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2916378974914551}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lwc.2024.3488859","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lwc.2024.3488859","pdf_url":null,"source":{"id":"https://openalex.org/S2500830676","display_name":"IEEE Wireless Communications Letters","issn_l":"2162-2337","issn":["2162-2337","2162-2345"],"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 Wireless Communications Letters","raw_type":"journal-article"},{"id":"pmh:oai:hub.hku.hk:10722/353228","is_oa":false,"landing_page_url":"https://hub.hku.hk/handle/10722/353228","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W3081492798","https://openalex.org/W3166791908","https://openalex.org/W3174174431","https://openalex.org/W4210624746","https://openalex.org/W4312051474","https://openalex.org/W4312958552","https://openalex.org/W4313350178","https://openalex.org/W4313419334","https://openalex.org/W4319302797","https://openalex.org/W4392152102","https://openalex.org/W4393252833","https://openalex.org/W4400277245","https://openalex.org/W6765779288","https://openalex.org/W6802036239","https://openalex.org/W6861363789"],"related_works":["https://openalex.org/W2121324502","https://openalex.org/W1592366631","https://openalex.org/W2619710173","https://openalex.org/W4247130340","https://openalex.org/W2270221717","https://openalex.org/W133561096","https://openalex.org/W622526920","https://openalex.org/W2007621757","https://openalex.org/W4256415979","https://openalex.org/W2187328420"],"abstract_inverted_index":{"This":[0],"letter":[1],"studies":[2],"an":[3,75],"efficient":[4,76],"multimodal":[5],"data":[6,53,83,98,161],"communication":[7],"scheme":[8],"for":[9],"video":[10,27,52,62,77,88,97,115,125],"conferencing.":[11],"In":[12,91],"our":[13],"considered":[14],"system,":[15,74],"a":[16,19,71,103,131],"speaker":[17,34],"gives":[18],"talk":[20],"to":[21,138,164],"the":[22,33,61,64,121,140,145,151,157,168,172],"audiences,":[23],"with":[24,106],"talking":[25,86],"head":[26,87],"and":[28,40,46,55,95,111,114,124],"audio":[29,44,94,113,123],"being":[30],"transmitted.":[31],"Since":[32],"does":[35],"not":[36],"frequently":[37],"change":[38],"posture":[39],"high-fidelity":[41],"transmission":[42,78],"of":[43,144,159,171],"(speech":[45],"music)":[47],"is":[48],"required,":[49],"redundant":[50],"visual":[51],"exists":[54],"can":[56,155],"be":[57],"removed":[58],"by":[59,84,162],"generating":[60,85],"from":[63,89],"audio.":[65,90],"To":[66],"this":[67],"end,":[68],"we":[69],"propose":[70],"wave-to-video":[72],"(Wav2Vid)":[73],"framework":[79],"that":[80,150],"reduces":[81],"transmitted":[82,101,160],"particular,":[92],"full-duration":[93],"short-duration":[96],"are":[99],"synchronously":[100],"through":[102],"wireless":[104],"channel,":[105],"neural":[107],"networks":[108],"(NNs)":[109],"extracting":[110],"encoding":[112],"semantics.":[116],"The":[117],"receiver":[118],"then":[119],"combines":[120],"decoded":[122],"data,":[126],"as":[127,129],"well":[128],"uses":[130],"generative":[132],"adversarial":[133],"network":[134],"(GAN)":[135],"based":[136],"model":[137],"generate":[139],"lip":[141],"movement":[142],"videos":[143],"speaker.":[146],"Simulation":[147],"results":[148],"show":[149],"proposed":[152],"Wav2Vid":[153],"system":[154],"reduce":[156],"amount":[158],"up":[163],"83%":[165],"while":[166],"maintaining":[167],"perceptual":[169],"quality":[170],"generated":[173],"conferencing":[174],"video.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":11}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
