{"id":"https://openalex.org/W4414691237","doi":"https://doi.org/10.1109/icassp55912.2026.11461767","title":"Generating Moving 3d Soundscapes with Latent Diffusion Models","display_name":"Generating Moving 3d Soundscapes with Latent Diffusion Models","publication_year":2026,"publication_date":"2026-04-21","ids":{"openalex":"https://openalex.org/W4414691237","doi":"https://doi.org/10.1109/icassp55912.2026.11461767"},"language":"en","primary_location":{"id":"doi:10.1109/icassp55912.2026.11461767","doi":"https://doi.org/10.1109/icassp55912.2026.11461767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp55912.2026.11461767","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/2507.07318","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119791815","display_name":"Christian Templin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christian Templin","raw_affiliation_strings":["Stevens Institute of Technology,Hoboken,NJ,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology,Hoboken,NJ,USA","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yanda Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I173759888","display_name":"Hunan Normal University","ror":"https://ror.org/053w1zy07","country_code":"CN","type":"education","lineage":["https://openalex.org/I173759888"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanda Zhu","raw_affiliation_strings":["Hunan Normal University,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan Normal University,Changsha,China","institution_ids":["https://openalex.org/I173759888"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101941841","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0003-4139-8193","observed_orcids":["https://orcid.org/0000-0003-4139-8193"]},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Stevens Institute of Technology,Hoboken,NJ,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology,Hoboken,NJ,USA","institution_ids":["https://openalex.org/I108468826"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00502715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2856","last_page":"2860"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.7275000214576721,"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":0.7275000214576721,"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":0.09839999675750732,"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":0.09610000252723694,"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/first-order-ambisonics","display_name":"first-order Ambisonics","score":0.8629999756813049},{"id":"https://openalex.org/keywords/spatial-audio","display_name":"spatial audio","score":0.628000020980835},{"id":"https://openalex.org/keywords/text-to-audio-generation","display_name":"text-to-audio generation","score":0.8140000104904175},{"id":"https://openalex.org/keywords/latent-diffusion-models","display_name":"latent diffusion models","score":0.8899999856948853},{"id":"https://openalex.org/keywords/moving-sound-sources","display_name":"moving sound sources","score":0.968999981880188},{"id":"https://openalex.org/keywords/spatial-localization","display_name":"spatial localization","score":0.5889999866485596},{"id":"https://openalex.org/keywords/immersive-audio","display_name":"immersive audio","score":0.414000004529953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7200999855995178},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5877000093460083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5496000051498413},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5332000255584717},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5206000208854675},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5127999782562256},{"id":"https://openalex.org/C47726159","wikidata":"https://www.wikidata.org/wiki/Q457547","display_name":"Ambisonics","level":3,"score":0.4788999855518341},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4625000059604645},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.46140000224113464},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3978999853134155},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3871999979019165},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C142795923","wikidata":"https://www.wikidata.org/wiki/Q1358257","display_name":"Soundscape","level":3,"score":0.35690000653266907},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.3433000147342682},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3409000039100647},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.29330000281333923},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C140631703","wikidata":"https://www.wikidata.org/wiki/Q34678","display_name":"Stereophonic sound","level":3,"score":0.27140000462532043},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp55912.2026.11461767","doi":"https://doi.org/10.1109/icassp55912.2026.11461767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp55912.2026.11461767","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:2507.07318","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.07318","pdf_url":"https://arxiv.org/pdf/2507.07318","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.07318","doi":"https://doi.org/10.48550/arxiv.2507.07318","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.07318","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:2507.07318","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.07318","pdf_url":"https://arxiv.org/pdf/2507.07318","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":null,"license_id":null,"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Spatial":[0],"audio":[1,16,67],"has":[2],"become":[3],"central":[4],"to":[5,21,48,150],"immersive":[6],"applications":[7],"such":[8],"as":[9],"VR/AR,":[10],"cinema,":[11],"and":[12,26,90,99,109,128,135,146],"music.":[13],"Existing":[14],"generative":[15],"models":[17,41],"are":[18],"largely":[19],"limited":[20],"mono":[22],"or":[23],"stereo":[24],"formats":[25],"cannot":[27],"capture":[28],"the":[29,57],"full":[30],"3D":[31],"localization":[32,159],"cues":[33],"available":[34],"in":[35,78],"first-order":[36],"Ambisonics":[37],"(FOA).":[38],"Recent":[39],"FOA":[40,66,121],"extend":[42],"text-to-audio":[43,152],"generation":[44],"but":[45],"remain":[46],"restricted":[47],"static":[49,127],"sources.":[50,74],"In":[51],"this":[52],"work,":[53],"we":[54,111],"introduce":[55],"SonicMotion,":[56],"first":[58],"end-to-end":[59],"latent":[60],"diffusion":[61],"framework":[62],"capable":[63],"of":[64,116],"generating":[65],"with":[68,131],"explicit":[69],"control":[70],"over":[71,117],"moving":[72],"sound":[73],"SonicMotion":[75,141],"is":[76],"implemented":[77],"two":[79],"variations:":[80],"1)":[81],"a":[82,92,113],"descriptive":[83],"model":[84,94],"conditioned":[85,95],"on":[86,96],"natural":[87],"language":[88],"prompts,":[89],"2)":[91],"parametric":[93],"both":[97,126],"text":[98],"spatial":[100,158],"trajectory":[101],"parameters":[102],"for":[103],"higher":[104],"precision.":[105],"To":[106],"support":[107],"training":[108],"evaluation,":[110],"construct":[112],"new":[114],"dataset":[115],"one":[118],"million":[119],"simulated":[120],"caption":[122],"pairs":[123],"that":[124,140],"include":[125],"dynamic":[129],"sources":[130],"annotated":[132],"azimuth,":[133],"elevation,":[134],"motion":[136],"attributes.":[137],"Experiments":[138],"show":[139],"achieves":[142],"state-of-the-art":[143],"semantic":[144],"alignment":[145],"perceptual":[147],"quality":[148],"comparable":[149],"leading":[151],"systems,":[153],"while":[154],"uniquely":[155],"attaining":[156],"low":[157],"error.":[160]},"counts_by_year":[],"updated_date":"2026-10-06T10:28:23.643775","created_date":"2025-10-10T00:00:00"}