{"id":"https://openalex.org/W4408345779","doi":"https://doi.org/10.1109/icassp49660.2025.10888008","title":"NAT3DSound: 3D Spatial Sound Field Synthesis with Multi-Modal Non-Autoregressive Transformer","display_name":"NAT3DSound: 3D Spatial Sound Field Synthesis with Multi-Modal Non-Autoregressive Transformer","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345779","doi":"https://doi.org/10.1109/icassp49660.2025.10888008"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888008","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":"https://openalex.org/A5113392266","display_name":"Fuming You","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fuming You","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011787904","display_name":"Rongjie Huang","orcid":"https://orcid.org/0000-0002-1695-9000"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongjie Huang","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100677422","display_name":"Boyang Zhang","orcid":"https://orcid.org/0000-0002-0895-6002"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyang Zhang","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068548095","display_name":"Yongqi Wang","orcid":"https://orcid.org/0000-0003-1292-0384"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqi Wang","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077830473","display_name":"Zhiqing Hong","orcid":"https://orcid.org/0000-0003-3682-4290"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqing Hong","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101409714","display_name":"Zhimeng Zhang","orcid":"https://orcid.org/0000-0002-3695-1129"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhimeng Zhang","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5113392266"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04860696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10860","display_name":"Speech and Audio Processing","score":0.9940000176429749,"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":0.9940000176429749,"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":0.9905999898910522,"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/T11309","display_name":"Music and Audio Processing","score":0.9868999719619751,"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":0.6164641976356506},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5728490352630615},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5712378621101379},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.504848062992096},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4365120232105255},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.394137442111969},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2048037350177765},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1892610788345337},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.17759639024734497},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12896260619163513},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07551175355911255},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.05854150652885437},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.056151002645492554}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6164641976356506},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5728490352630615},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5712378621101379},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.504848062992096},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4365120232105255},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.394137442111969},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2048037350177765},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1892610788345337},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.17759639024734497},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12896260619163513},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07551175355911255},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.05854150652885437},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.056151002645492554},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888008","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":21,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2800288142","https://openalex.org/W2963609956","https://openalex.org/W2970906079","https://openalex.org/W2982624843","https://openalex.org/W2988975212","https://openalex.org/W3034742263","https://openalex.org/W3096780661","https://openalex.org/W3215615641","https://openalex.org/W4307323391","https://openalex.org/W4313021454","https://openalex.org/W4381786045","https://openalex.org/W4385263018","https://openalex.org/W4388684552","https://openalex.org/W6688799136","https://openalex.org/W6754782314","https://openalex.org/W6771467084","https://openalex.org/W6849367332","https://openalex.org/W6853515095","https://openalex.org/W6856434366","https://openalex.org/W6860273036"],"related_works":["https://openalex.org/W2171218219","https://openalex.org/W1972271943","https://openalex.org/W2150410159","https://openalex.org/W4327525404","https://openalex.org/W4287185323","https://openalex.org/W3150905897","https://openalex.org/W1520183331","https://openalex.org/W2734842993","https://openalex.org/W2168175994","https://openalex.org/W2049473509"],"abstract_inverted_index":{"3D":[0,18,98],"spatial":[1,27,69,99],"sound":[2,19,64,100],"field":[3,20,65],"synthesis":[4],"takes":[5],"the":[6,22,50,63,142,159],"head-mounted":[7],"audio":[8,28,47,78,116],"signals":[9,48],"and":[10,15,83,113,130,155,168],"body":[11],"poses":[12],"as":[13],"input":[14,46,79,115],"renders":[16],"a":[17,39,56,93,106,119,132],"around":[21],"center":[23],"body,":[24],"in":[25,150,163],"which":[26,102],"can":[29],"be":[30],"inferred":[31],"at":[32,175],"any":[33],"arbitrary":[34],"position.":[35],"To":[36,87],"achieve":[37],"this,":[38],"multi-modal":[40],"system":[41],"is":[42,59],"required":[43],"to":[44,61],"spatialize":[45],"with":[49,66,122],"guidance":[51],"of":[52,68,104,144,161,165],"pose":[53],"streams.":[54],"Then,":[55],"numerical":[57],"method":[58],"used":[60],"render":[62],"hundreds":[67],"audio.":[70],"However,":[71],"there":[72],"exist":[73],"several":[74],"challenges":[75],"including":[76],"hybrid":[77],"signals,":[80,117],"cross-modal":[81,128],"matching,":[82],"few":[84],"data":[85],"resources.":[86],"address":[88],"them,":[89],"we":[90,140],"propose":[91],"NAT3DSound,":[92],"unit-based":[94],"framework":[95],"for":[96,110,126,136,147],"high-quality":[97],"synthesis,":[101],"consists":[103],"1)":[105],"general":[107],"tokenization":[108],"scheme":[109],"both":[111],"dense":[112],"impulsive":[114],"2)":[118],"non-autoregressive":[120],"transformer":[121],"multi-scale":[123],"modality":[124],"fusion":[125],"efficient":[127],"alignment":[129],"3)":[131],"parallel":[133],"sampling":[134],"strategy":[135],"fast":[137],"prediction.":[138],"Furthermore,":[139],"investigate":[141],"feasibility":[143],"acoustic":[145],"pre-training":[146],"low-resource":[148],"learning":[149],"data-scarce":[151],"scenarios.":[152],"Extensive":[153],"experiments":[154],"ablation":[156],"studies":[157],"demonstrate":[158],"effectiveness":[160],"NAT3DSound":[162],"terms":[164],"spatialization":[166],"quality":[167],"generalization":[169],"ability.":[170],"Audio":[171],"samples":[172],"are":[173],"available":[174],"http://NAT3DSound.github.io":[176]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}