{"id":"https://openalex.org/W4392910582","doi":"https://doi.org/10.1109/icassp48485.2024.10445928","title":"Mtdiffusion: Multi-Task Diffusion Model With Dual-Unet for Foley Sound Generation","display_name":"Mtdiffusion: Multi-Task Diffusion Model With Dual-Unet for Foley Sound Generation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910582","doi":"https://doi.org/10.1109/icassp48485.2024.10445928"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445928","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10445928","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/A5038123809","display_name":"Anbin Qi","orcid":"https://orcid.org/0009-0009-1015-7494"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Anbin Qi","raw_affiliation_strings":["Beijing Institute of Technology,School of Information and Electronics","School of Information and Electronics, Beijing Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Information and Electronics","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100642395","display_name":"Xiang Xie","orcid":"https://orcid.org/0000-0002-5135-0110"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Xie","raw_affiliation_strings":["Beijing Institute of Technology,School of Information and Electronics","School of Information and Electronics, Beijing Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Information and Electronics","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100378497","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0002-3653-9951"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Wang","raw_affiliation_strings":["Beijing Institute of Technology,School of Information and Electronics","School of Information and Electronics, Beijing Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Information and Electronics","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038123809"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.3362,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4784106,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"461","last_page":"465"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9944999814033508,"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/T10860","display_name":"Speech and Audio Processing","score":0.9923999905586243,"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":0.7480549812316895},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.638633668422699},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6291446685791016},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.570796549320221},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5223965644836426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48174285888671875},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4723074436187744},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4470500648021698},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4246603548526764},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40447506308555603},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38986092805862427},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38034799695014954},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14360260963439941},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08797129988670349}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480549812316895},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.638633668422699},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6291446685791016},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.570796549320221},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5223965644836426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48174285888671875},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4723074436187744},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4470500648021698},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4246603548526764},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40447506308555603},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38986092805862427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38034799695014954},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14360260963439941},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08797129988670349},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445928","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10445928","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":[],"awards":[{"id":"https://openalex.org/G5249178904","display_name":null,"funder_award_id":"Grant No. 6","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6471985988","display_name":null,"funder_award_id":"62071039","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1959608418","https://openalex.org/W2624871570","https://openalex.org/W2752796333","https://openalex.org/W2760103357","https://openalex.org/W2766219058","https://openalex.org/W2908510526","https://openalex.org/W2913340405","https://openalex.org/W2972478942","https://openalex.org/W2975414524","https://openalex.org/W2996286887","https://openalex.org/W3110257065","https://openalex.org/W3121370741","https://openalex.org/W3141797743","https://openalex.org/W3214281017","https://openalex.org/W3215615641","https://openalex.org/W4212774754","https://openalex.org/W4250482878","https://openalex.org/W4318752004","https://openalex.org/W4319779318","https://openalex.org/W4367359628","https://openalex.org/W4385245566","https://openalex.org/W4386601626","https://openalex.org/W6640963894","https://openalex.org/W6739365718","https://openalex.org/W6747491877","https://openalex.org/W6754005058","https://openalex.org/W6757817989","https://openalex.org/W6765775151","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6783867762","https://openalex.org/W6786375611","https://openalex.org/W6788990321","https://openalex.org/W6796464841","https://openalex.org/W6849109464","https://openalex.org/W6852019497"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W2043093291","https://openalex.org/W2363545964"],"abstract_inverted_index":{"It":[0],"is":[1,69],"a":[2,103],"common":[3],"method":[4],"to":[5,17,26],"quantify":[6],"the":[7,23,28,32,37,41,65,112,120,133,138,141],"latent":[8],"in":[9],"audio":[10,101,135],"generation":[11],"and":[12,47,59,74,79,84,126,129,140],"then":[13],"use":[14],"diffusion":[15,42,94],"models":[16],"estimate":[18,76],"noise":[19,46,78],"or":[20],"data":[21,25,80],"from":[22],"corrupted":[24],"generate":[27,98],"quantized":[29],"latent.":[30],"Unlike":[31],"method,":[33],"we":[34,63,91],"consider":[35],"that":[36],"targets":[38],"estimated":[39],"by":[40,72],"model":[43,110],"include":[44],"both":[45,77,127],"data,":[48],"rather":[49],"than":[50],"just":[51],"one":[52],"of":[53,122,132],"them.":[54],"Based":[55],"on":[56,111,145],"this":[57],"idea":[58],"multi-task":[60],"learning":[61],"methods,":[62],"design":[64],"network":[66],"Dual-Unet,":[67],"which":[68,96],"simply":[70],"modified":[71],"U-net":[73],"can":[75,97],"simultaneously.":[81],"Combining":[82],"Dual-Unet":[83],"Variational":[85],"AutoEncoders":[86],"with":[87,102],"Residual":[88],"Vector":[89],"Quantizer,":[90],"propose":[92],"Multitask":[93],"model(MTDiffusion),":[95],"foley":[99],"sound":[100],"given":[104],"label.":[105],"We":[106],"validate":[107],"our":[108,123],"proposed":[109,124],"DCASE":[113,147],"task7B":[114],"dataset.":[115],"The":[116],"experimental":[117],"results":[118],"show":[119],"effectiveness":[121],"model,":[125],"subjective":[128],"objective":[130],"metrics":[131],"generated":[134],"significantly":[136],"exceed":[137],"baseline":[139],"first":[142],"place":[143],"ranked":[144],"2023":[146],"task7B.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}