{"id":"https://openalex.org/W4408354290","doi":"https://doi.org/10.1109/icassp49660.2025.10888864","title":"MambaFoley: Foley Sound Generation using Selective State-Space Models","display_name":"MambaFoley: Foley Sound Generation using Selective State-Space Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354290","doi":"https://doi.org/10.1109/icassp49660.2025.10888864"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":null,"display_name":"Marco Furio Colombo","orcid":null},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Furio Colombo","raw_affiliation_strings":["Politecnico di Milano,Informazione e Bioingegneria (DEIB),Dipartimento di Elettronica,Milan,Italy,20133"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Informazione e Bioingegneria (DEIB),Dipartimento di Elettronica,Milan,Italy,20133","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056089196","display_name":"Francesca Ronchini","orcid":"https://orcid.org/0000-0001-6897-1645"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesca Ronchini","raw_affiliation_strings":["Politecnico di Milano,Informazione e Bioingegneria (DEIB),Dipartimento di Elettronica,Milan,Italy,20133"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Informazione e Bioingegneria (DEIB),Dipartimento di Elettronica,Milan,Italy,20133","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007911573","display_name":"Luca Comanducci","orcid":"https://orcid.org/0000-0002-4167-5173"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Comanducci","raw_affiliation_strings":["Politecnico di Milano,Informazione e Bioingegneria (DEIB),Dipartimento di Elettronica,Milan,Italy,20133"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Informazione e Bioingegneria (DEIB),Dipartimento di Elettronica,Milan,Italy,20133","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082156387","display_name":"Fabio Antonacci","orcid":"https://orcid.org/0000-0003-4545-0315"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Antonacci","raw_affiliation_strings":["Politecnico di Milano,Informazione e Bioingegneria (DEIB),Dipartimento di Elettronica,Milan,Italy,20133"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Informazione e Bioingegneria (DEIB),Dipartimento di Elettronica,Milan,Italy,20133","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2561,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.93568433,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.9990000128746033,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9958000183105469,"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/sound","display_name":"Sound (geography)","score":0.661028265953064},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6172382235527039},{"id":"https://openalex.org/keywords/foley","display_name":"Foley","score":0.5709512233734131},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5178842544555664},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3737126588821411},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11788889765739441},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09224545955657959}],"concepts":[{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.661028265953064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6172382235527039},{"id":"https://openalex.org/C110446960","wikidata":"https://www.wikidata.org/wiki/Q762316","display_name":"Foley","level":2,"score":0.5709512233734131},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5178842544555664},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3737126588821411},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11788889765739441},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09224545955657959},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1295745","is_oa":false,"landing_page_url":"https://hdl.handle.net/11311/1295745","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2038484192","https://openalex.org/W2526050071","https://openalex.org/W2760103357","https://openalex.org/W3094550259","https://openalex.org/W4205689591","https://openalex.org/W4367359628","https://openalex.org/W4372263438","https://openalex.org/W4392902957","https://openalex.org/W4392903391","https://openalex.org/W4392910528","https://openalex.org/W4392931592","https://openalex.org/W4396877837","https://openalex.org/W4402111418","https://openalex.org/W4402111582","https://openalex.org/W4402112008","https://openalex.org/W4403363072","https://openalex.org/W4408345986","https://openalex.org/W6732429163","https://openalex.org/W6739901393","https://openalex.org/W6757220786","https://openalex.org/W6761628794","https://openalex.org/W6765779288","https://openalex.org/W6767440493","https://openalex.org/W6779823529","https://openalex.org/W6796762324","https://openalex.org/W6797906067","https://openalex.org/W6802912272","https://openalex.org/W6803444062","https://openalex.org/W6810325043","https://openalex.org/W6840815571","https://openalex.org/W6849416043","https://openalex.org/W6852019497","https://openalex.org/W6853759707","https://openalex.org/W6854083324","https://openalex.org/W6859298233","https://openalex.org/W6863679278","https://openalex.org/W6868789466","https://openalex.org/W6870148787","https://openalex.org/W6870299770"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2523036031","https://openalex.org/W4237383858","https://openalex.org/W3211743321","https://openalex.org/W2016968289","https://openalex.org/W2021759681","https://openalex.org/W2011071567","https://openalex.org/W4256291417"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,38],"deep":[3],"learning":[4],"have":[5,73],"led":[6],"to":[7,55,81,102,111],"widespread":[8],"use":[9],"of":[10,32,43,50,66,105,130],"techniques":[11],"for":[12,35,40,120],"audio":[13,67],"content":[14],"generation,":[15],"notably":[16],"employing":[17],"Denoising":[18],"Diffusion":[19],"Probabilistic":[20],"Models":[21,71],"(DDPM)":[22],"across":[23],"various":[24],"tasks.":[25],"Among":[26],"these,":[27],"Foley":[28,122,140],"Sound":[29],"Synthesis":[30],"is":[31,53,108],"particular":[33],"interest":[34],"its":[36],"role":[37],"applications":[39],"the":[41,47,63,103,109,113,121,128,131],"creation":[42],"multimedia":[44],"content.":[45],"Given":[46],"temporal-dependent":[48],"nature":[49],"sound,":[51],"it":[52,136],"crucial":[54],"design":[56],"generative":[57,142],"models":[58],"that":[59],"can":[60],"effectively":[61],"handle":[62],"sequential":[64],"modeling":[65],"samples.":[68],"Selective":[69],"State-Space":[70],"(SSMs)":[72],"recently":[74,114],"been":[75],"proposed":[76,83,115,132],"as":[77,118],"a":[78,98,138],"valid":[79],"alternative":[80],"previously":[82],"techniques,":[84],"demonstrating":[85],"competitive":[86],"performance":[87],"with":[88,137],"lower":[89],"computational":[90],"complexity.":[91],"In":[92],"this":[93],"paper,":[94],"we":[95,134],"introduce":[96],"MambaFoley,":[97],"diffusion-based":[99],"model":[100,143],"that,":[101],"best":[104],"our":[106],"knowledge,":[107],"first":[110],"leverage":[112],"SSM":[116],"known":[117],"Mamba":[119],"sound":[123,141],"generation":[124],"task.":[125],"To":[126],"evaluate":[127],"effectiveness":[129],"method,":[133],"compare":[135],"state-of-the-art":[139],"using":[144],"both":[145],"objective":[146],"and":[147],"subjective":[148],"analyses.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
