{"id":"https://openalex.org/W4408347147","doi":"https://doi.org/10.1109/icassp49660.2025.10888882","title":"Diff-SAGe: End-to-End Spatial Audio Generation Using Diffusion Models","display_name":"Diff-SAGe: End-to-End Spatial Audio Generation Using Diffusion Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408347147","doi":"https://doi.org/10.1109/icassp49660.2025.10888882"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888882","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":"conference-paper","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":"Saksham Singh Kushwaha","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saksham Singh Kushwaha","raw_affiliation_strings":["The University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029277359","display_name":"Jianbo Ma","orcid":"https://orcid.org/0000-0003-0046-0835"},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jianbo Ma","raw_affiliation_strings":["Dolby Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040088188","display_name":"M. E. Thomas","orcid":null},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mark R. P. Thomas","raw_affiliation_strings":["Dolby Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101835756","display_name":"Yapeng Tian","orcid":"https://orcid.org/0000-0003-1423-4513"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yapeng Tian","raw_affiliation_strings":["The University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114336246","display_name":"Avery Bruni","orcid":null},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Avery Bruni","raw_affiliation_strings":["Dolby Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9983999729156494,"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":0.9983999729156494,"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":0.984499990940094,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.6459615230560303},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6013530492782593},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5254877209663391},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15495815873146057},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.082652747631073}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6459615230560303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6013530492782593},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5254877209663391},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15495815873146057},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.082652747631073},{"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/icassp49660.2025.10888882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888882","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2031865865","https://openalex.org/W2763188033","https://openalex.org/W2775794021","https://openalex.org/W2810934215","https://openalex.org/W2905118706","https://openalex.org/W2982382207","https://openalex.org/W2982624843","https://openalex.org/W3157866890","https://openalex.org/W4236344233","https://openalex.org/W4285044837","https://openalex.org/W4367359628","https://openalex.org/W4386764032","https://openalex.org/W4387969125","https://openalex.org/W4390872297","https://openalex.org/W4392904420","https://openalex.org/W4403840763","https://openalex.org/W6628691990","https://openalex.org/W6754782314","https://openalex.org/W6757220786","https://openalex.org/W6760529994","https://openalex.org/W6779923105","https://openalex.org/W6783867762","https://openalex.org/W6792340124","https://openalex.org/W6843731886","https://openalex.org/W6846539466","https://openalex.org/W6849109464","https://openalex.org/W6849416043","https://openalex.org/W6851290578","https://openalex.org/W6854445938","https://openalex.org/W6856607740","https://openalex.org/W6866562102","https://openalex.org/W6869582388","https://openalex.org/W6875334955","https://openalex.org/W6960281013"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Spatial":[0],"audio":[1,16,39],"is":[2],"a":[3,45,54,75,91,99],"crucial":[4,85],"component":[5],"in":[6],"creating":[7],"immersive":[8],"experiences.":[9],"Traditional":[10],"simulation-based":[11,124],"approaches":[12],"to":[13],"generate":[14],"spatial":[15,29,38,60,88],"rely":[17],"on":[18,113],"expertise,":[19],"have":[20],"limited":[21],"scalability,":[22],"and":[23,28,43,57,129],"assume":[24],"independence":[25],"between":[26],"semantic":[27],"information.":[30],"To":[31],"address":[32],"these":[33],"issues,":[34],"we":[35,116],"explore":[36],"end-to-end":[37],"generation.":[40],"We":[41,62],"introduce":[42],"formulate":[44],"new":[46],"task":[47],"of":[48,105],"generating":[49],"first-order":[50],"Ambisonics":[51],"(FOA)":[52],"given":[53],"sound":[55,58],"category":[56],"source":[59],"location.":[61],"propose":[63],"Diff-SAGe,":[64],"an":[65],"end-to-end,":[66],"flow-based":[67],"diffusion-transformer":[68],"model":[69],"for":[70,79,86],"this":[71],"task.":[72],"Diff-SAGe":[73],"utilizes":[74],"complex":[76],"spectrogram":[77],"representation":[78],"FOA,":[80],"preserving":[81],"the":[82,95,103],"phase":[83],"information":[84],"accurate":[87],"cues.":[89],"Additionally,":[90],"multi-conditional":[92],"encoder":[93],"integrates":[94],"input":[96],"conditions":[97],"into":[98],"unified":[100],"representation,":[101],"guiding":[102],"generation":[104],"FOA":[106],"waveforms":[107],"from":[108],"noise.":[109],"Through":[110],"extensive":[111],"evaluations":[112],"two":[114],"datasets,":[115],"demonstrate":[117],"that":[118],"our":[119],"method":[120],"consistently":[121],"outperforms":[122],"traditional":[123],"baselines":[125],"across":[126],"both":[127],"objective":[128],"subjective":[130],"metrics.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}