{"id":"https://openalex.org/W4416799559","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249371","title":"Towards Robust Stereo 3-D SELD: A Study of Perceptual Features and Data Augmentation","display_name":"Towards Robust Stereo 3-D SELD: A Study of Perceptual Features and Data Augmentation","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799559","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249371"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249371","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5118747081","display_name":"Jun-Wei Yeow","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jun-Wei Yeow","raw_affiliation_strings":["Nanyang Technological University,Smart Nation TRANS Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Smart Nation TRANS Lab,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102175655","display_name":"Ee-Leng Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ee-Leng Tan","raw_affiliation_strings":["Nanyang Technological University,Smart Nation TRANS Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Smart Nation TRANS Lab,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082360965","display_name":"Santi Peksi","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Santi Peksi","raw_affiliation_strings":["Nanyang Technological University,Smart Nation TRANS Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Smart Nation TRANS Lab,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072584895","display_name":"Woon\u2010Seng Gan","orcid":"https://orcid.org/0000-0002-7143-1823"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Woon-Seng Gan","raw_affiliation_strings":["Nanyang Technological University,Smart Nation TRANS Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Smart Nation TRANS Lab,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064367564","display_name":"Qirui Huang","orcid":"https://orcid.org/0009-0007-9491-7950"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qirui Huang","raw_affiliation_strings":["Nanyang Technological University,Smart Nation TRANS Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Smart Nation TRANS Lab,Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38711143,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"95","last_page":"100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7287999987602234,"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":0.7287999987602234,"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":0.2484000027179718,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.006599999964237213,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ambisonics","display_name":"Ambisonics","score":0.8156999945640564},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6212999820709229},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5569999814033508},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.43700000643730164},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.42320001125335693},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.3928999900817871}],"concepts":[{"id":"https://openalex.org/C47726159","wikidata":"https://www.wikidata.org/wiki/Q457547","display_name":"Ambisonics","level":3,"score":0.8156999945640564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6628000140190125},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6212999820709229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5623000264167786},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5569999814033508},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.43700000643730164},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.42320001125335693},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41040000319480896},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3928999900817871},{"id":"https://openalex.org/C126057942","wikidata":"https://www.wikidata.org/wiki/Q35158","display_name":"Stereoscopy","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2745000123977661},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26840001344680786},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2662000060081482}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249371","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":16,"referenced_works":["https://openalex.org/W2166547995","https://openalex.org/W2810934215","https://openalex.org/W2917254586","https://openalex.org/W2936774411","https://openalex.org/W2982680886","https://openalex.org/W3163193264","https://openalex.org/W3202467894","https://openalex.org/W3203177955","https://openalex.org/W3203468141","https://openalex.org/W3206329344","https://openalex.org/W3213455868","https://openalex.org/W4312654700","https://openalex.org/W4324116353","https://openalex.org/W4392904420","https://openalex.org/W4404577061","https://openalex.org/W4411867138"],"related_works":[],"abstract_inverted_index":{"Sound":[0,7,26],"Event":[1,8],"Localization":[2],"and":[3,11,61,105],"Detection":[4,9],"(SELD)":[5],"unifies":[6],"(SED)":[10],"Direction-of-Arrival":[12],"(DOA)":[13],"estimation":[14],"to":[15,39],"deliver":[16],"a":[17,90],"unified":[18],"spatiotemporal":[19],"representation":[20],"of":[21,49,84,92],"auditory":[22],"scenes.":[23],"By":[24],"incorporating":[25],"Distance":[27],"Estimation":[28],"(SDE),":[29],"SELD":[30,54,124],"extends":[31],"into":[32,116],"three":[33],"dimensions":[34],"(3-D":[35],"SELD),":[36],"enabling":[37],"systems":[38,125],"estimate":[40],"not":[41],"only":[42],"the":[43,47,80],"directions":[44],"but":[45],"also":[46],"distances":[48],"sound":[50],"sources.":[51],"While":[52],"3-D":[53,86,123],"has":[55],"seen":[56],"considerable":[57],"progress":[58],"with":[59],"ambisonic":[60,106],"multi-microphone":[62],"arrays,":[63],"it":[64],"remains":[65],"underexplored":[66],"for":[67,103,120,126],"stereo":[68,95],"formats":[69],"commonly":[70],"found":[71],"in":[72],"consumer":[73,128],"electronics.":[74],"In":[75],"this":[76,137],"paper,":[77],"we":[78,111],"present":[79],"first":[81],"comprehensive":[82],"study":[83],"stereo-based":[85,129],"SELD.":[87],"We":[88],"evaluate":[89],"range":[91],"perceptually":[93],"motivated":[94],"features,":[96],"alongside":[97],"proven":[98],"augmentation":[99],"methods":[100],"originally":[101],"developed":[102],"multi-channel":[104],"audio.":[107],"From":[108],"these":[109],"results,":[110],"then":[112],"distill":[113],"our":[114],"insights":[115],"clear":[117],"best-practice":[118],"guidelines":[119],"developing":[121],"robust":[122],"everyday":[127],"applications.":[130],"Our":[131],"implementation":[132],"is":[133],"publicly":[134],"available":[135],"at":[136],"repository":[138],"<sup":[139],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[140],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>1https://github.com/itsjunwei/NTU_SNTL_Task3.":[141]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}