{"id":"https://openalex.org/W4375868912","doi":"https://doi.org/10.1109/icassp49357.2023.10096353","title":"VarietySound: Timbre-Controllable Video to Sound Generation Via Unsupervised Information Disentanglement","display_name":"VarietySound: Timbre-Controllable Video to Sound Generation Via Unsupervised Information Disentanglement","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868912","doi":"https://doi.org/10.1109/icassp49357.2023.10096353"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096353","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/A5012657658","display_name":"Chenye Cui","orcid":"https://orcid.org/0009-0009-9083-1628"},"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":true,"raw_author_name":"Chenye Cui","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"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":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088179161","display_name":"Yi Ren","orcid":"https://orcid.org/0000-0001-9889-5460"},"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":"Yi Ren","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065126806","display_name":"Jinglin Liu","orcid":"https://orcid.org/0000-0002-9905-3887"},"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":"Jinglin Liu","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011787904","display_name":"Rongjie Huang","orcid":"https://orcid.org/0000-0002-1695-9000"},"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":"Rongjie Huang","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060844215","display_name":"Feiyang Chen","orcid":null},"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":"Feiyang Chen","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065838678","display_name":"Zhefeng Wang","orcid":"https://orcid.org/0000-0001-6703-2064"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhefeng Wang","raw_affiliation_strings":["Huawei Cloud"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025894594","display_name":"Baoxing Huai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baoxing Huai","raw_affiliation_strings":["Huawei Cloud"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004882141","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0003-2139-8807"},"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":"Fei Wu","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5012657658"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":1.8608,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85994218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9954000115394592,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9905999898910522,"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/timbre","display_name":"Timbre","score":0.9261617660522461},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.83388352394104},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.8215351104736328},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6645724177360535},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.648150622844696},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.6031452417373657},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4829956293106079},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.48082435131073},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4667750895023346},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.41106724739074707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3864416480064392},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1962527334690094},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.16796690225601196},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0913105309009552}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.9261617660522461},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.83388352394104},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.8215351104736328},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6645724177360535},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.648150622844696},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.6031452417373657},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4829956293106079},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.48082435131073},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4667750895023346},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.41106724739074707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3864416480064392},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1962527334690094},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.16796690225601196},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0913105309009552},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096353","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2107860279","https://openalex.org/W2511428026","https://openalex.org/W2560662850","https://openalex.org/W2570915410","https://openalex.org/W2593414223","https://openalex.org/W2808707363","https://openalex.org/W2912947616","https://openalex.org/W2963807156","https://openalex.org/W2964345931","https://openalex.org/W3046890131","https://openalex.org/W3092028330","https://openalex.org/W3160567113","https://openalex.org/W3187009280","https://openalex.org/W4285603330","https://openalex.org/W4293665662","https://openalex.org/W6638667902","https://openalex.org/W6729831399","https://openalex.org/W6752365561","https://openalex.org/W6757445682","https://openalex.org/W6757817989","https://openalex.org/W6762533536","https://openalex.org/W6776390925","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6802805937"],"related_works":["https://openalex.org/W2040048036","https://openalex.org/W2607529793","https://openalex.org/W1512864190","https://openalex.org/W2978163245","https://openalex.org/W3033263360","https://openalex.org/W1590604789","https://openalex.org/W2088690926","https://openalex.org/W2792033502","https://openalex.org/W2065633372","https://openalex.org/W3043119899"],"abstract_inverted_index":{"Video-to-sound":[0],"generation":[1,16],"aims":[2],"to":[3,35,82,100],"generate":[4,20,145],"realistic":[5],"and":[6,68,91,116,125,156],"natural":[7],"sound":[8,32,58,86],"given":[9,63,104],"a":[10,21,60,64,69,98,122,126],"video":[11,66,155],"input.":[12],"However,":[13],"previous":[14],"video-to-sound":[15],"methods":[17,47],"can":[18,144],"only":[19],"random":[22],"or":[23],"average":[24],"timbre":[25,44,62,158],"without":[26],"any":[27],"controls":[28],"of":[29,56],"the":[30,36,42,54,102,110,130,137,161],"generated":[31,111],"timbre,":[33],"leading":[34],"problem":[37],"that":[38,141],"people":[39],"cannot":[40],"obtain":[41],"desired":[43],"under":[45],"these":[46,105],"sometimes.":[48],"In":[49],"this":[50,75],"paper,":[51],"we":[52,77,96,119],"propose":[53],"task":[55],"generating":[57],"with":[59,149,152,160],"specific":[61],"silent":[65],"input":[67],"reference":[70,162],"audio":[71,87,103,147],"sample.":[72],"To":[73,108],"solve":[74],"task,":[76],"first":[78],"use":[79,97],"three":[80],"encoders":[81],"disentangle":[83],"each":[84],"target":[85],"into":[88],"temporal,":[89],"acoustic,":[90],"background":[92],"information":[93],"respectively,":[94],"then":[95],"decoder":[99],"reconstruct":[101],"disentangled":[106],"representations.":[107],"make":[109],"result":[112],"achieve":[113],"better":[114],"quality":[115],"temporal":[117,127],"alignment,":[118],"also":[120],"adopt":[121],"mel":[123],"discriminator":[124,128],"for":[129],"adversarial":[131],"training.":[132],"Our":[133,164],"experimental":[134],"results":[135],"on":[136,169],"VAS":[138],"dataset":[139],"demonstrate":[140],"our":[142],"method":[143],"high-quality":[146],"samples":[148],"good":[150],"synchronization":[151],"events":[153],"in":[154],"high":[157],"similarity":[159],"audio.":[163],"demos":[165],"have":[166],"been":[167],"published":[168],"https://conferencedemos.github.io/icassp23/.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}