{"id":"https://openalex.org/W4416249947","doi":"https://doi.org/10.1109/waspaa66052.2025.11230921","title":"Learning Robust Spatial Representations from Binaural Audio through Feature Distillation","display_name":"Learning Robust Spatial Representations from Binaural Audio through Feature Distillation","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416249947","doi":"https://doi.org/10.1109/waspaa66052.2025.11230921"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230921","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":"conference-paper","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/A5055991258","display_name":"Holger Severin Bovbjerg","orcid":"https://orcid.org/0000-0002-8735-739X"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Holger Severin Bovbjerg","raw_affiliation_strings":["Aalborg University,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023894109","display_name":"Jan \u00d8stergaard","orcid":"https://orcid.org/0000-0002-3724-6114"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jan \u00d8stergaard","raw_affiliation_strings":["Aalborg University,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075467383","display_name":"Jesper Jensen","orcid":"https://orcid.org/0000-0002-5007-4097"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jesper Jensen","raw_affiliation_strings":["Aalborg University,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110494768","display_name":"Zheng-Hua Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":["Aalborg University,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"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":0.9757000207901001,"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":0.9757000207901001,"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":0.00930000003427267,"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":0.0066999997943639755,"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":0.7961999773979187},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5957000255584717},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.583899974822998},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5706999897956848},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5663999915122986},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.483599990606308},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.35749998688697815},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.34540000557899475}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.7961999773979187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7085000276565552},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6327999830245972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6132000088691711},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5957000255584717},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.583899974822998},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5706999897956848},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5663999915122986},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.483599990606308},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3181999921798706},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.30410000681877136},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.29249998927116394},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27799999713897705},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2563000023365021},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25600001215934753},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230921","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:pure.atira.dk:publications/bc33cf35-6a53-41e9-890c-3a399f188687","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/bc33cf35-6a53-41e9-890c-3a399f188687","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331522","display_name":"William Demant Fonden","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1603075283","https://openalex.org/W2046317813","https://openalex.org/W2100818340","https://openalex.org/W2109447493","https://openalex.org/W2113638573","https://openalex.org/W2127000566","https://openalex.org/W2586068394","https://openalex.org/W2592109325","https://openalex.org/W2696967604","https://openalex.org/W2765962757","https://openalex.org/W2940285530","https://openalex.org/W2947942791","https://openalex.org/W2972943112","https://openalex.org/W2995181338","https://openalex.org/W3097777922","https://openalex.org/W3113264499","https://openalex.org/W3132830522","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4213337799","https://openalex.org/W4221140371","https://openalex.org/W4281492411","https://openalex.org/W4297841316","https://openalex.org/W4312314094","https://openalex.org/W4362653188","https://openalex.org/W4366967194","https://openalex.org/W4375869479","https://openalex.org/W4402447547","https://openalex.org/W4404269162","https://openalex.org/W4404782746","https://openalex.org/W4404835573"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"deep":[1],"representation":[2,41],"learning":[3,16],"has":[4],"shown":[5],"strong":[6],"performance":[7,117],"in":[8,118],"multiple":[9],"audio":[10,21],"tasks.":[11],"However,":[12],"its":[13],"use":[14,27,91],"for":[15,48,105,125],"spatial":[17,40,54,87],"representations":[18],"from":[19,58,73],"multichannel":[20],"is":[22],"underexplored.":[23],"We":[24],"investigate":[25],"the":[26,46,86,92,112],"of":[28,42],"a":[29,38,78,98],"pretraining":[30],"stage":[31],"based":[32],"on":[33],"feature":[34,88],"distillation":[35],"to":[36,63,96,130],"learn":[37],"robust":[39],"binaural":[43,60],"speech":[44,61,76],"without":[45],"need":[47],"data":[49],"labels.":[50,66],"In":[51],"this":[52],"framework,":[53],"features":[55,69],"are":[56,70],"computed":[57],"clean":[59,68],"samples":[62],"form":[64],"prediction":[65],"These":[67],"then":[71],"predicted":[72],"corresponding":[74],"augmented":[75],"using":[77],"neural":[79],"network.":[80],"After":[81],"pretraining,":[82],"we":[83,103],"throw":[84],"away":[85],"predictor":[89],"and":[90,120,134],"learned":[93],"encoder":[94],"weights":[95],"initialize":[97],"DoA":[99,106],"estimation":[100],"model":[101],"which":[102],"fine-tune":[104],"estimation.":[107],"Our":[108],"experiments":[109],"demonstrate":[110],"that":[111],"pretrained":[113],"models":[114,133],"show":[115],"improved":[116],"noisy":[119],"reverberant":[121],"environments":[122],"after":[123],"fine-tuning":[124],"direction-of-arrival":[126],"estimation,":[127],"when":[128],"compared":[129],"fully":[131],"supervised":[132],"classic":[135],"signal":[136],"processing":[137],"methods.":[138]},"counts_by_year":[],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-11-14T00:00:00"}