{"id":"https://openalex.org/W4417119751","doi":"https://doi.org/10.1109/icassp55912.2026.11462711","title":"MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation","display_name":"MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation","publication_year":2026,"publication_date":"2026-04-21","ids":{"openalex":"https://openalex.org/W4417119751","doi":"https://doi.org/10.1109/icassp55912.2026.11462711"},"language":"en","primary_location":{"id":"doi:10.1109/icassp55912.2026.11462711","doi":"https://doi.org/10.1109/icassp55912.2026.11462711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp55912.2026.11462711","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.09065","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050144186","display_name":"Akira Takahashi","orcid":"https://orcid.org/0000-0003-4289-9838","observed_orcids":["https://orcid.org/0000-0003-4289-9838"]},"institutions":[{"id":"https://openalex.org/I4210143797","display_name":"Sony (Japan)","ror":"https://ror.org/04wzv3n59","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210143797"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akira Takahashi","raw_affiliation_strings":["Sony Group Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Japan","institution_ids":["https://openalex.org/I4210143797"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104117184","display_name":"Shusuke Takahashi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210143797","display_name":"Sony (Japan)","ror":"https://ror.org/04wzv3n59","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210143797"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shusuke Takahashi","raw_affiliation_strings":["Sony Group Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Japan","institution_ids":["https://openalex.org/I4210143797"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140","observed_orcids":["https://orcid.org/0000-0002-6806-6140"]},"institutions":[{"id":"https://openalex.org/I4210143797","display_name":"Sony (Japan)","ror":"https://ror.org/04wzv3n59","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210143797"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Mitsufuji","raw_affiliation_strings":["Sony Group Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Japan","institution_ids":["https://openalex.org/I4210143797"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210143797"],"apc_list":null,"apc_paid":null,"fwci":10.6738,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.94570682,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"15667","last_page":"15671"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9330999851226807,"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":0.9330999851226807,"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/T10860","display_name":"Speech and Audio Processing","score":0.0471000000834465,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.00860000029206276,"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/audio-source-separation","display_name":"audio source separation","score":0.8930000066757202},{"id":"https://openalex.org/keywords/video-to-audio-generation","display_name":"video-to-audio generation","score":0.9229999780654907},{"id":"https://openalex.org/keywords/generative-models","display_name":"generative models","score":0.6029999852180481},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.9259999990463257},{"id":"https://openalex.org/keywords/foundation-models","display_name":"foundation models","score":0.4169999957084656}],"concepts":[{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7531999945640564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.685699999332428},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6200000047683716},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5511999726295471},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5414999723434448},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5379999876022339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5058000087738037},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4165000021457672},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39320001006126404},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37529999017715454},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3125},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.29350000619888306},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.25850000977516174}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp55912.2026.11462711","doi":"https://doi.org/10.1109/icassp55912.2026.11462711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp55912.2026.11462711","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.09065","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.09065","pdf_url":"https://arxiv.org/pdf/2510.09065","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.09065","doi":"https://doi.org/10.48550/arxiv.2510.09065","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.09065","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.09065","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.09065","pdf_url":"https://arxiv.org/pdf/2510.09065","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417119751.pdf","grobid_xml":"https://content.openalex.org/works/W4417119751.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,53],"introduce":[1],"MMAudioSep,":[2],"a":[3,14,30],"generative":[4,33,73],"model":[5,39,44,98],"for":[6,92,102,118],"video/text-queried":[7],"sound":[8,93,112],"separation":[9,64,94],"that":[10,87],"is":[11,78,124],"founded":[12],"on":[13,69],"pretrained":[15,31],"video-to-audio":[16,104],"model.":[17],"By":[18],"leveraging":[19],"knowledge":[20],"about":[21],"the":[22,38,43,55,81,97,100,108],"relationship":[23],"between":[24],"video/text":[25],"and":[26,72,75],"audio":[27,32],"learned":[28],"through":[29],"model,":[34],"we":[35,85],"can":[36],"train":[37],"more":[40],"efficiently,":[41],"i.e.,":[42],"does":[45],"not":[46],"need":[47],"to":[48,62,80,115],"be":[49,116],"trained":[50],"from":[51],"scratch.":[52],"evaluate":[54],"performance":[56],"of":[57,110],"MMAudioSep":[58],"by":[59],"comparing":[60],"it":[61,77],"existing":[63],"models,":[65],"including":[66],"models":[67,114],"based":[68],"both":[70],"deterministic":[71],"approaches,":[74],"find":[76],"superior":[79],"baseline":[82],"models.":[83],"Furthermore,":[84],"demonstrate":[86],"even":[88],"after":[89],"acquiring":[90],"functionality":[91],"via":[95],"fine-tuning,":[96],"retains":[99],"ability":[101],"original":[103],"generation.":[105],"This":[106],"highlights":[107],"potential":[109],"foundational":[111],"generation":[113],"adopted":[117],"sound-related":[119],"downstream":[120],"tasks.":[121],"Our":[122],"code":[123],"available":[125],"at":[126],"https://github.com/sony/mmaudiosep.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-06T10:28:23.643775","created_date":"2025-10-14T00:00:00"}