{"id":"https://openalex.org/W4375868855","doi":"https://doi.org/10.1109/icassp49357.2023.10096358","title":"Audio-Driven Facial Landmark Generation in Violin Performance using 3DCNN Network with Self Attention Model","display_name":"Audio-Driven Facial Landmark Generation in Violin Performance using 3DCNN Network with Self Attention Model","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868855","doi":"https://doi.org/10.1109/icassp49357.2023.10096358"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096358","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5102168849","display_name":"Ting-Wei Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I87354575","display_name":"National Chengchi University","ror":"https://ror.org/03rqk8h36","country_code":"TW","type":"education","lineage":["https://openalex.org/I87354575"]},{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Ting-Wei Lin","raw_affiliation_strings":["Taiwan International Graduate Program,Social Networks and Human-Centered Computing","Institute of Information Science, Academia Sinica, Taipei, Taiwan","Social Networks and Human-Centered Computing, Taiwan International Graduate Program","Department of Computer Science, National Chengchi University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Taiwan International Graduate Program,Social Networks and Human-Centered Computing","institution_ids":[]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Social Networks and Human-Centered Computing, Taiwan International Graduate Program","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science, National Chengchi University, Taipei, Taiwan","institution_ids":["https://openalex.org/I87354575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005169817","display_name":"Chao-Lin Liu","orcid":"https://orcid.org/0000-0002-4093-1497"},"institutions":[{"id":"https://openalex.org/I87354575","display_name":"National Chengchi University","ror":"https://ror.org/03rqk8h36","country_code":"TW","type":"education","lineage":["https://openalex.org/I87354575"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chao-Lin Liu","raw_affiliation_strings":["National Chengchi University,Department of Computer Science,Taipei,Taiwan","Department of Computer Science, National Chengchi University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Chengchi University,Department of Computer Science,Taipei,Taiwan","institution_ids":["https://openalex.org/I87354575"]},{"raw_affiliation_string":"Department of Computer Science, National Chengchi University, Taipei, Taiwan","institution_ids":["https://openalex.org/I87354575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038264558","display_name":"Li Su","orcid":"https://orcid.org/0000-0003-4275-8832"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li Su","raw_affiliation_strings":["Academia Sinica,Institute of Information Science,Taipei,Taiwan","Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Institute of Information Science,Taipei,Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102168849"],"corresponding_institution_ids":["https://openalex.org/I4210098366","https://openalex.org/I87354575"],"apc_list":null,"apc_paid":null,"fwci":0.2612,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55814585,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"4","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12032","display_name":"Multisensory perception and integration","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12032","display_name":"Multisensory perception and integration","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.9020161628723145},{"id":"https://openalex.org/keywords/violin","display_name":"Violin","score":0.8827347755432129},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7316373586654663},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6534839868545532},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40765321254730225},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3801378607749939},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.23331445455551147}],"concepts":[{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.9020161628723145},{"id":"https://openalex.org/C129554576","wikidata":"https://www.wikidata.org/wiki/Q8355","display_name":"Violin","level":2,"score":0.8827347755432129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7316373586654663},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6534839868545532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40765321254730225},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3801378607749939},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.23331445455551147},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096358","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321041","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784"},{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1588539311","https://openalex.org/W1978405625","https://openalex.org/W2040448642","https://openalex.org/W2102533671","https://openalex.org/W2108598243","https://openalex.org/W2115252128","https://openalex.org/W2147611605","https://openalex.org/W2169755138","https://openalex.org/W2194775991","https://openalex.org/W2609448651","https://openalex.org/W2780124704","https://openalex.org/W2795230330","https://openalex.org/W2903065126","https://openalex.org/W2980581183","https://openalex.org/W3002137088","https://openalex.org/W3015674789","https://openalex.org/W3018757597","https://openalex.org/W3035169015","https://openalex.org/W3085146247","https://openalex.org/W3100204393","https://openalex.org/W3102619627","https://openalex.org/W3116722996","https://openalex.org/W3123730414","https://openalex.org/W3155389124","https://openalex.org/W4224920309","https://openalex.org/W4225984289","https://openalex.org/W4226409981","https://openalex.org/W6635087628","https://openalex.org/W6677618333","https://openalex.org/W6684771281","https://openalex.org/W6750333878","https://openalex.org/W6756864065","https://openalex.org/W6768827828","https://openalex.org/W6777046832","https://openalex.org/W6789679135","https://openalex.org/W6811501851"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0,44,99],"a":[1,49,86],"music":[2,31,39],"scenario,":[3],"both":[4],"auditory":[5],"and":[6,52,79,91,115],"visual":[7],"elements":[8],"are":[9,117],"essential":[10],"to":[11],"achieve":[12],"an":[13],"outstanding":[14],"performance.":[15,32,63],"Recent":[16],"research":[17],"has":[18],"focused":[19],"on":[20,109,119],"the":[21,69,73,100,120],"generation":[22,36],"of":[23],"body":[24],"movements":[25],"or":[26],"fingering":[27],"from":[28],"audio":[29,78],"in":[30,38,61],"The":[33,113],"audio-driven":[34,95],"face":[35,111],"technique":[37],"performance":[40,77],"is":[41,68],"still":[42],"deficient.":[43],"this":[45,67],"paper,":[46],"we":[47,102],"compile":[48],"violin":[50,62,76],"soundtrack":[51],"facial":[53,59,81,96],"expression":[54,97],"dataset":[55,71,116],"(VSFE)":[56],"for":[57,94],"modeling":[58],"expressions":[60],"To":[64],"our":[65,104],"knowledge,":[66],"first":[70],"mapping":[72],"relationship":[74],"between":[75],"musicians\u2019":[80],"expressions.":[82],"We":[83],"then":[84],"propose":[85],"3DCNN":[87],"network":[88],"with":[89,106],"self-attention":[90],"residual":[92],"blocks":[93],"generation.":[98,112],"experiments,":[101],"compare":[103],"methods":[105],"three":[107],"baselines":[108],"talking":[110],"codes":[114],"available":[118],"Github":[121],"(https://github.com/kevinlin91/icassp_music2face).":[122]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}
