{"id":"https://openalex.org/W3167586735","doi":"https://doi.org/10.1109/waspaa52581.2021.9632781","title":"DPLM: A Deep Perceptual Spatial-Audio Localization Metric","display_name":"DPLM: A Deep Perceptual Spatial-Audio Localization Metric","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3167586735","doi":"https://doi.org/10.1109/waspaa52581.2021.9632781","mag":"3167586735"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa52581.2021.9632781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.14180","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075510192","display_name":"Pranay Manocha","orcid":"https://orcid.org/0000-0003-3284-5908"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pranay Manocha","raw_affiliation_strings":["Facebook Reality Labs Research, Redmond, WA, USA","Princeton University, Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080751032","display_name":"Anurag Kumar","orcid":"https://orcid.org/0000-0002-1164-144X"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anurag Kumar","raw_affiliation_strings":["Facebook Reality Labs Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040562171","display_name":"Buye Xu","orcid":"https://orcid.org/0000-0002-3027-7567"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Buye Xu","raw_affiliation_strings":["Facebook Reality Labs Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042577114","display_name":"Anjali Menon","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anjali Menon","raw_affiliation_strings":["Facebook Reality Labs Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072548521","display_name":"Israel D. Gebru","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Israel D. Gebru","raw_affiliation_strings":["Facebook Reality Labs Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108520440","display_name":"Vamsi Krishna Ithapu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vamsi K. Ithapu","raw_affiliation_strings":["Facebook Reality Labs Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004601228","display_name":"Paul Calamia","orcid":"https://orcid.org/0000-0002-0401-6996"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Calamia","raw_affiliation_strings":["Facebook Reality Labs Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5075510192"],"corresponding_institution_ids":["https://openalex.org/I20089843","https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":0.1539,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42191799,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"6","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9991999864578247,"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":0.9970999956130981,"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/binaural-recording","display_name":"Binaural recording","score":0.8131940364837646},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7659012675285339},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6972430348396301},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6643848419189453},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6323803663253784},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5631402730941772},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5151987671852112},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.46145355701446533},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4453403651714325},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33579587936401367},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0760229229927063},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07429161667823792},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06592598557472229}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.8131940364837646},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7659012675285339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6972430348396301},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6643848419189453},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6323803663253784},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5631402730941772},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5151987671852112},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.46145355701446533},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4453403651714325},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33579587936401367},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0760229229927063},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07429161667823792},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06592598557472229},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/waspaa52581.2021.9632781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.14180","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.14180","pdf_url":"https://arxiv.org/pdf/2105.14180","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"mag:3167586735","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2105.14180.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2105.14180","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2105.14180","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.14180","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.14180","pdf_url":"https://arxiv.org/pdf/2105.14180","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1493897031","https://openalex.org/W1515109179","https://openalex.org/W1520657064","https://openalex.org/W1561928502","https://openalex.org/W1842577739","https://openalex.org/W2009649672","https://openalex.org/W2097117768","https://openalex.org/W2125620494","https://openalex.org/W2136682440","https://openalex.org/W2164944484","https://openalex.org/W2183341477","https://openalex.org/W2398217754","https://openalex.org/W2549440896","https://openalex.org/W2768337397","https://openalex.org/W2935930396","https://openalex.org/W2940285530","https://openalex.org/W2948105160","https://openalex.org/W2948208658","https://openalex.org/W2948364140","https://openalex.org/W2948526624","https://openalex.org/W2952218014","https://openalex.org/W2953163324","https://openalex.org/W2962785568","https://openalex.org/W2972443522","https://openalex.org/W2985229398","https://openalex.org/W3002439978","https://openalex.org/W3023239811","https://openalex.org/W3033731578","https://openalex.org/W3097934054","https://openalex.org/W3111598519","https://openalex.org/W3129121609","https://openalex.org/W3138953166","https://openalex.org/W3160506022","https://openalex.org/W3211188239","https://openalex.org/W6629412591","https://openalex.org/W6630456326","https://openalex.org/W6631116650","https://openalex.org/W6633492010","https://openalex.org/W6638676062","https://openalex.org/W6712077227","https://openalex.org/W6729461096","https://openalex.org/W6762806790","https://openalex.org/W6763156250","https://openalex.org/W6772622344","https://openalex.org/W6779923105","https://openalex.org/W6787050168","https://openalex.org/W6792340124"],"related_works":["https://openalex.org/W3140252313","https://openalex.org/W2970678032","https://openalex.org/W2169770604","https://openalex.org/W2964931564","https://openalex.org/W3212068911","https://openalex.org/W2883980546","https://openalex.org/W2986131686","https://openalex.org/W3110013267","https://openalex.org/W2918282358","https://openalex.org/W3161507032","https://openalex.org/W625673579","https://openalex.org/W2929983093","https://openalex.org/W156101013","https://openalex.org/W2470720735","https://openalex.org/W3034892239","https://openalex.org/W2950966753","https://openalex.org/W2402233488","https://openalex.org/W3132010254","https://openalex.org/W3000306765","https://openalex.org/W2768688139"],"abstract_inverted_index":{"Subjective":[0],"evaluations":[1],"are":[2,22],"critical":[3],"for":[4,28,52,79],"assessing":[5],"the":[6,37,41,105],"perceptual":[7,42],"realism":[8],"of":[9,39,44,81,101,107],"sounds":[10],"in":[11],"audio-synthesis":[12],"driven":[13],"technologies":[14],"like":[15],"augmented":[16],"and":[17,30],"virtual":[18],"reality.":[19],"However,":[20],"they":[21],"challenging":[23],"to":[24,58],"set":[25,100],"up,":[26],"fatiguing":[27],"users,":[29],"expensive.":[31],"In":[32],"this":[33],"work,":[34],"we":[35,48],"tackle":[36],"problem":[38],"capturing":[40],"characteristics":[43],"localizing":[45],"sounds.":[46],"Specifically,":[47],"propose":[49],"a":[50,54,98],"framework":[51],"building":[53],"general-purpose":[55],"quality":[56],"metric":[57,87],"assess":[59],"spatial":[60],"localization":[61,69],"differences":[62],"between":[63],"two":[64],"binaural":[65],"recordings.":[66],"We":[67],"model":[68],"similarity":[70],"by":[71],"utilizing":[72],"activation-level":[73],"distances":[74],"from":[75],"deep":[76],"networks":[77],"trained":[78],"direction":[80],"arrival":[82],"(DOA)":[83],"estimation.":[84],"Our":[85],"proposed":[86],"(DPLM)":[88],"outperforms":[89],"baseline":[90],"metrics":[91],"on":[92,97],"correlation":[93],"with":[94],"subjective":[95],"ratings":[96],"diverse":[99],"datasets,":[102],"even":[103],"without":[104],"benefit":[106],"any":[108],"human-labeled":[109],"training":[110],"data.":[111]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}