{"id":"https://openalex.org/W4402351754","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650012","title":"Editing Audio-Driven Talking Head Based on Audio Information","display_name":"Editing Audio-Driven Talking Head Based on Audio Information","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402351754","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650012"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650012","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650012","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/A5103052046","display_name":"Rui Lang","orcid":"https://orcid.org/0009-0002-3444-0461"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rui Lang","raw_affiliation_strings":["Xiamen University,School of Informatics,Xiamen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5103052046"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17552648,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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":0.9973000288009644,"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":0.9972000122070312,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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":0.774644136428833},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5430251359939575},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.4678780734539032},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4612191617488861},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4147099554538727},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.41216039657592773},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.35822370648384094},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.29296183586120605}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.774644136428833},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5430251359939575},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.4678780734539032},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4612191617488861},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4147099554538727},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.41216039657592773},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.35822370648384094},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.29296183586120605},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650012","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650012","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2769666294","https://openalex.org/W2891205112","https://openalex.org/W2895311831","https://openalex.org/W2949662773","https://openalex.org/W2962770929","https://openalex.org/W2962785568","https://openalex.org/W2981263323","https://openalex.org/W2990138404","https://openalex.org/W3019952993","https://openalex.org/W3081492798","https://openalex.org/W3101631197","https://openalex.org/W3104792420","https://openalex.org/W3109114891","https://openalex.org/W3167297682","https://openalex.org/W3173102319","https://openalex.org/W3174763799","https://openalex.org/W3178406257","https://openalex.org/W3180770160","https://openalex.org/W3195529437","https://openalex.org/W3202128205","https://openalex.org/W3209059054","https://openalex.org/W3211147706","https://openalex.org/W3215121054","https://openalex.org/W4296438045","https://openalex.org/W4311034013","https://openalex.org/W4311804540","https://openalex.org/W4311806224","https://openalex.org/W4312301053","https://openalex.org/W4312472600","https://openalex.org/W4312477574","https://openalex.org/W4312546057","https://openalex.org/W4312959196","https://openalex.org/W4312990833","https://openalex.org/W4379527433","https://openalex.org/W4381568416","https://openalex.org/W4385490328","https://openalex.org/W4386072021","https://openalex.org/W4386075768","https://openalex.org/W4390872116","https://openalex.org/W6754420807","https://openalex.org/W6765779288","https://openalex.org/W6780218876","https://openalex.org/W6849049266","https://openalex.org/W6853577421"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W1975359510","https://openalex.org/W2494533082","https://openalex.org/W4214771044","https://openalex.org/W4387698063","https://openalex.org/W4382560817","https://openalex.org/W3004352674","https://openalex.org/W3110605476","https://openalex.org/W1803351015","https://openalex.org/W2363106653"],"abstract_inverted_index":{"Editing":[0],"audio-driven":[1,218],"talking":[2,118,219],"head":[3,119,180,220],"is":[4,57,64,83],"a":[5,116,178,184],"relatively":[6],"new":[7],"direction":[8],"in":[9,33],"the":[10,21,30,34,42,53,60,78,89,102,105,110,163,212,225],"field":[11],"of":[12,44,101,104,169,214],"computer":[13],"vision":[14],"and":[15,48,77,97,138,149,199],"still":[16],"faces":[17],"many":[18],"challenges.":[19],"First,":[20],"existing":[22,67],"methods":[23,70],"do":[24],"not":[25],"fully":[26],"take":[27],"into":[28],"account":[29],"information":[31,131],"contained":[32],"driving":[35,54],"audio,":[36],"which":[37,202],"can":[38,81,203],"easily":[39,204],"lead":[40,205],"to":[41,74,94,98,141,182,206,224,228],"problem":[43],"mismatch":[45],"between":[46,197],"audio":[47,55,124,130,135,198],"video":[49,200,231],"features":[50,152,173],"(for":[51],"example,":[52],"emotion":[56,63],"happy,":[58],"but":[59],"corresponding":[61],"facial":[62,92,143,151,207],"calm).":[65],"Second,":[66],"face":[68,158,165],"editing":[69,120],"are":[71],"often":[72],"limited":[73],"one":[75],"mode,":[76],"variety":[79],"they":[80],"produce":[82],"limited.":[84],"Finally,":[85],"we":[86,127,176],"would":[87],"like":[88],"final":[90],"generated":[91],"animation":[93],"be":[95],"undistorted":[96],"retain":[99],"some":[100],"identity":[103,172],"original":[106,171],"image.":[107],"To":[108,160],"address":[109],"above":[111],"problems,":[112],"this":[113],"paper":[114],"proposes":[115],"novel":[117],"method":[121,216],"based":[122],"on":[123],"information.":[125],"Specifically,":[126],"obtain":[128],"comprehensive":[129],"by":[132,153],"introducing":[133,189],"multiple":[134],"feature":[136],"classifiers":[137],"use":[139,177],"it":[140],"guide":[142],"editing.":[144,221],"We":[145],"generate":[146],"more":[147],"diverse":[148],"detailed":[150,230],"combining":[154],"two":[155],"different":[156],"dimensional":[157],"editors.":[159],"ensure":[161],"that":[162],"edited":[164],"retains":[166],"as":[167,174],"much":[168],"its":[170],"possible,":[175],"3D":[179],"model":[181],"drive":[183],"single":[185],"image,":[186],"rather":[187],"than":[188],"latent":[190],"space":[191],"or":[192],"establishing":[193],"complex":[194],"cross-modal":[195],"associations":[196],"frames,":[201],"distortion.":[208],"Extensive":[209],"experiments":[210],"demonstrate":[211],"superiority":[213],"our":[215],"for":[217],"Please":[222],"go":[223],"link":[226],"below":[227],"view":[229],"results:":[232],"https://drive.google.com/drive/folders/10T1nIktZciG6Cih_UEUOrg0YKXG6KM-C?usp=sharing":[233]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}