{"id":"https://openalex.org/W4415538782","doi":"https://doi.org/10.1145/3746027.3755571","title":"A Multimodal Evaluation Framework for Spatial Audio Playback Systems: From Localization to Listener Preference","display_name":"A Multimodal Evaluation Framework for Spatial Audio Playback Systems: From Localization to Listener Preference","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538782","doi":"https://doi.org/10.1145/3746027.3755571"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755571","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5103228451","display_name":"Changhao Pan","orcid":"https://orcid.org/0009-0004-6023-1764"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changhao Pan","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China and Shanghai Artificial Intelligence Laboratory, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0004-6023-1764","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China and Shanghai Artificial Intelligence Laboratory, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104320351","display_name":"Wenxiang Guo","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":false,"raw_author_name":"Wenxiang Guo","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0006-7997-4140","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092336773","display_name":"Yu Zhang","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":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0007-4594-0281","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiyuan Zhu","orcid":"https://orcid.org/0009-0006-1276-0420"},"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":"Zhiyuan Zhu","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0006-1276-0420","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066441297","display_name":"Zhetao Chen","orcid":"https://orcid.org/0009-0006-9232-9066"},"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":"Zhetao Chen","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0006-9232-9066","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Han Wang","orcid":"https://orcid.org/0009-0004-5004-8851"},"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":"Han Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-5004-8851","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","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/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China and Shanghai Artificial Intelligence Laboratory, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-6121-0384","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China and Shanghai Artificial Intelligence Laboratory, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210123185"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"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":0.33991815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7006","last_page":"7015"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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":0.9912999868392944,"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/reverberation","display_name":"Reverberation","score":0.6008999943733215},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.593500018119812},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.5181999802589417},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.5128999948501587},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.47429999709129333},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4034000039100647},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3869999945163727},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.35569998621940613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7426999807357788},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6008999943733215},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.593500018119812},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.5181999802589417},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5169000029563904},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.5128999948501587},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.47429999709129333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43309998512268066},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3499000072479248},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.33980000019073486},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.29580000042915344},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755571","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W317957491","https://openalex.org/W1552314771","https://openalex.org/W2114213946","https://openalex.org/W2593116425","https://openalex.org/W3031309253","https://openalex.org/W3159481202","https://openalex.org/W4402112153","https://openalex.org/W4402756608","https://openalex.org/W4406519716","https://openalex.org/W7117960283"],"related_works":[],"abstract_inverted_index":{"Spatial":[0],"audio":[1,28,54,63,74,102,155],"playback":[2,39,78],"defines":[3],"immersive":[4],"listening.":[5],"However,":[6],"objective":[7],"evaluation":[8,50,121],"methods":[9],"for":[10,52],"perceptual":[11,94,111,150],"dimensions":[12],"like":[13],"sound":[14,17],"field":[15],"and":[16,30,35,56,80,88,109,125],"image":[18],"remain":[19],"underdeveloped,":[20],"hindered":[21],"by":[22],"the":[23,31],"lack":[24],"of":[25,33,71],"fine-grained":[26,89,110],"spatial":[27,53,62,73,101,154],"datasets":[29],"neglect":[32],"echoes":[34],"reverberation":[36,126],"in":[37,136],"diverse":[38],"conditions.":[40],"To":[41],"address":[42],"these":[43],"challenges,":[44],"we":[45],"propose":[46],"MESA,":[47],"a":[48,59,100,140],"multi-modal":[49],"framework":[51],"systems,":[55],"introduce":[57],"PSA-MOS,":[58],"high-quality":[60,72],"multi-scene":[61],"dataset.":[64],"Specifically:":[65],"1)":[66],"PSA-MOS":[67],"provides":[68],"50":[69],"hours":[70],"recordings":[75],"spanning":[76],"6":[77],"scenarios":[79],"7":[81],"device":[82],"types,":[83],"with":[84,148],"detailed":[85],"localization":[86],"annotations":[87],"MOS":[90],"ratings":[91],"across":[92],"four":[93],"dimensions.":[95],"2)":[96],"We":[97],"develop":[98],"SAE-Encoder,":[99],"encoder":[103],"that":[104,131],"captures":[105],"both":[106],"acoustic-spatial":[107],"cues":[108],"patterns.":[112],"3)":[113],"MESA":[114,144],"integrates":[115],"visual":[116],"scene":[117],"context":[118],"to":[119],"enhance":[120],"robustness":[122],"through":[123],"echo":[124],"modeling.":[127],"Experimental":[128],"results":[129],"demonstrate":[130],"SAE-Encoder":[132],"achieves":[133],"superior":[134],"performance":[135],"SELD":[137],"tasks.":[138],"With":[139],"two-stage":[141],"training":[142],"strategy,":[143],"exhibits":[145],"strong":[146],"correlation":[147],"human":[149],"assessments,":[151],"effectively":[152],"guiding":[153],"quality":[156],"optimization.":[157],"The":[158],"demos":[159],"are":[160],"available":[161],"at":[162],"https://david-pigeon.github.io/mesaDemo.":[163]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-25T00:00:00"}
