{"id":"https://openalex.org/W4416250910","doi":"https://doi.org/10.1109/waspaa66052.2025.11231001","title":"Towards Perception-Informed Latent HRTF Representations","display_name":"Towards Perception-Informed Latent HRTF Representations","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416250910","doi":"https://doi.org/10.1109/waspaa66052.2025.11231001"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa66052.2025.11231001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11231001","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.02815","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100384568","display_name":"You Zhang","orcid":"https://orcid.org/0000-0002-4649-278X"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"You Zhang","raw_affiliation_strings":["University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067381155","display_name":"Andrew Francl","orcid":"https://orcid.org/0000-0001-6417-7866"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Francl","raw_affiliation_strings":["Meta Reality Labs Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102907601","display_name":"Ruohan Gao","orcid":"https://orcid.org/0000-0002-8346-1114"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruohan Gao","raw_affiliation_strings":["University of Maryland,College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004601228","display_name":"Paul Calamia","orcid":"https://orcid.org/0000-0002-0401-6996"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Calamia","raw_affiliation_strings":["Meta Reality Labs Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102749436","display_name":"Zhiyao Duan","orcid":"https://orcid.org/0000-0002-8334-9974"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyao Duan","raw_affiliation_strings":["University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037474835","display_name":"Ishwarya Ananthabhotla","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ishwarya Ananthabhotla","raw_affiliation_strings":["Meta Reality Labs Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research","institution_ids":["https://openalex.org/I4210128585"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100384568"],"corresponding_institution_ids":["https://openalex.org/I5388228"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32657278,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.6761000156402588,"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"}},"topics":[{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.6761000156402588,"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"}},{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.0706000030040741,"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"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.06509999930858612,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6251000165939331},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5013999938964844},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.48840001225471497},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.4871000051498413},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4745999872684479},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.46939998865127563},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.4645000100135803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6385999917984009},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6251000165939331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5490999817848206},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5013999938964844},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.48840001225471497},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.4871000051498413},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4745999872684479},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.46939998865127563},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.4645000100135803},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4253999888896942},{"id":"https://openalex.org/C91682802","wikidata":"https://www.wikidata.org/wiki/Q620538","display_name":"Multidimensional scaling","level":2,"score":0.4032000005245209},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3995000123977661},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32829999923706055},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.29420000314712524},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26989999413490295},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.26809999346733093},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2574999928474426}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11231001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11231001","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.02815","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.02815","pdf_url":"https://arxiv.org/pdf/2507.02815","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.02815","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.02815","pdf_url":"https://arxiv.org/pdf/2507.02815","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":36,"referenced_works":["https://openalex.org/W1587360517","https://openalex.org/W1964832178","https://openalex.org/W2054090614","https://openalex.org/W2089473323","https://openalex.org/W2763307249","https://openalex.org/W2769850798","https://openalex.org/W2804721500","https://openalex.org/W2939124443","https://openalex.org/W2999027282","https://openalex.org/W3003257820","https://openalex.org/W3044194010","https://openalex.org/W3045934380","https://openalex.org/W3114257826","https://openalex.org/W3140252313","https://openalex.org/W3160970338","https://openalex.org/W4214659619","https://openalex.org/W4226064907","https://openalex.org/W4241759446","https://openalex.org/W4285124635","https://openalex.org/W4285194056","https://openalex.org/W4287756134","https://openalex.org/W4313192087","https://openalex.org/W4367665481","https://openalex.org/W4372348473","https://openalex.org/W4383562880","https://openalex.org/W4386763486","https://openalex.org/W4392333968","https://openalex.org/W4392903946","https://openalex.org/W4404315969","https://openalex.org/W4404577459","https://openalex.org/W4405573926","https://openalex.org/W4406259645","https://openalex.org/W4407783224","https://openalex.org/W4408345590","https://openalex.org/W4408355970","https://openalex.org/W4415284388"],"related_works":[],"abstract_inverted_index":{"Personalized":[0],"head-related":[1],"transfer":[2],"functions":[3],"(HRTFs)":[4],"are":[5,53,89],"essential":[6],"for":[7,46,61,66,105],"ensuring":[8],"a":[9,35,47,57,103,110,115],"realistic":[10],"auditory":[11],"experience":[12],"over":[13],"headphones,":[14],"because":[15],"they":[16,70],"take":[17],"into":[18,109],"account":[19],"individual":[20],"anatomical":[21],"differences":[22],"that":[23,59,143],"affect":[24],"listening.":[25],"Most":[26],"machine":[27],"learning":[28],"approaches":[29],"to":[30,40,135,149,155],"HRTF":[31,87,139],"personalization":[32],"rely":[33],"on":[34],"learned":[36,55,86,133],"low-dimensional":[37],"latent":[38,51,112],"space":[39],"generate":[41],"or":[42],"select":[43],"custom":[44],"HRTFs":[45,108],"listener.":[48],"However,":[49],"these":[50,132],"representations":[52,88,134],"typically":[54],"in":[56],"manner":[58],"optimizes":[60],"spectral":[62],"reconstruction":[63],"but":[64],"not":[65,72],"perceptual":[67,76,93,98],"compatibility,":[68],"meaning":[69],"may":[71],"necessarily":[73],"align":[74],"with":[75,92],"distance.":[77],"In":[78],"this":[79],"work,":[80],"we":[81,100,127],"first":[82],"study":[83],"whether":[84],"traditionally":[85],"well":[90],"correlated":[91],"relations":[94],"using":[95],"auditory-based":[96],"objective":[97],"metrics;":[99],"then":[101],"propose":[102],"method":[104,145],"explicitly":[106],"embedding":[107],"perception-informed":[111],"space,":[113],"leveraging":[114],"metric-based":[116],"loss":[117],"function":[118],"and":[119],"supervision":[120],"via":[121],"Metric":[122],"Multidimensional":[123],"Scaling":[124],"(MMDS).":[125],"Finally,":[126],"demonstrate":[128],"the":[129,136,147],"applicability":[130],"of":[131,138],"task":[137],"personalization.":[140],"We":[141],"suggest":[142],"our":[144],"has":[146],"potential":[148],"render":[150],"personalized":[151],"spatial":[152],"audio,":[153],"leading":[154],"an":[156],"improved":[157],"listening":[158],"experience.":[159]},"counts_by_year":[],"updated_date":"2026-05-02T08:42:23.175194","created_date":"2025-10-10T00:00:00"}