{"id":"https://openalex.org/W4387835382","doi":"https://doi.org/10.1145/3586183.3606779","title":"Semantic Hearing: Programming Acoustic Scenes with Binaural\u00a0Hearables","display_name":"Semantic Hearing: Programming Acoustic Scenes with Binaural\u00a0Hearables","publication_year":2023,"publication_date":"2023-10-20","ids":{"openalex":"https://openalex.org/W4387835382","doi":"https://doi.org/10.1145/3586183.3606779"},"language":"en","primary_location":{"id":"doi:10.1145/3586183.3606779","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3586183.3606779","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3586183.3606779","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3586183.3606779","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080881573","display_name":"Bandhav Veluri","orcid":"https://orcid.org/0000-0002-5086-9092"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bandhav Veluri","raw_affiliation_strings":["Paul G. Allen Center for Computer Science & Engineering, University of Washington, United States"],"raw_orcid":"https://orcid.org/0000-0002-5086-9092","affiliations":[{"raw_affiliation_string":"Paul G. Allen Center for Computer Science & Engineering, University of Washington, United States","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035670633","display_name":"Malek Itani","orcid":"https://orcid.org/0009-0002-7249-2641"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Malek Itani","raw_affiliation_strings":["Paul G. Allen Center for Computer Science and Engineering, University of Washington, United States"],"raw_orcid":"https://orcid.org/0009-0002-7249-2641","affiliations":[{"raw_affiliation_string":"Paul G. Allen Center for Computer Science and Engineering, University of Washington, United States","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062650938","display_name":"Justin Chan","orcid":"https://orcid.org/0000-0002-1471-6187"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Chan","raw_affiliation_strings":["Computer Science & Engineering, University of Washington, United States"],"raw_orcid":"https://orcid.org/0000-0002-1471-6187","affiliations":[{"raw_affiliation_string":"Computer Science & Engineering, University of Washington, United States","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["Audio and AI, Microsoft, United States"],"raw_orcid":"https://orcid.org/0009-0003-7791-3545","affiliations":[{"raw_affiliation_string":"Audio and AI, Microsoft, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011077730","display_name":"Shyamnath Gollakota","orcid":"https://orcid.org/0000-0002-9863-3054"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shyamnath Gollakota","raw_affiliation_strings":["university of Washington, United States"],"raw_orcid":"https://orcid.org/0000-0002-9863-3054","affiliations":[{"raw_affiliation_string":"university of Washington, United States","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1733,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.96650984,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"15"},"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":0.9998000264167786,"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":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.7850711345672607},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.6807565689086914},{"id":"https://openalex.org/keywords/sound-localization","display_name":"Sound localization","score":0.4798792898654938},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4703032374382019},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4475739598274231},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.42043066024780273},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4195847809314728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25930291414260864},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13199859857559204},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08680707216262817}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7850711345672607},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.6807565689086914},{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.4798792898654938},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4703032374382019},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4475739598274231},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.42043066024780273},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4195847809314728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25930291414260864},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13199859857559204},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08680707216262817},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3586183.3606779","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3586183.3606779","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3586183.3606779","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2311.00320","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.00320","pdf_url":"https://arxiv.org/pdf/2311.00320","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3586183.3606779","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3586183.3606779","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3586183.3606779","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.6399999856948853,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387835382.pdf","grobid_xml":"https://content.openalex.org/works/W4387835382.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W2041645947","https://openalex.org/W2058733260","https://openalex.org/W2077856040","https://openalex.org/W2084529785","https://openalex.org/W2108668360","https://openalex.org/W2144685889","https://openalex.org/W2166682639","https://openalex.org/W2519091744","https://openalex.org/W2539508298","https://openalex.org/W2593116425","https://openalex.org/W2771361008","https://openalex.org/W2774707525","https://openalex.org/W2877975652","https://openalex.org/W2897647475","https://openalex.org/W2944972166","https://openalex.org/W2946439262","https://openalex.org/W2952218014","https://openalex.org/W2964058413","https://openalex.org/W2981816492","https://openalex.org/W2988200020","https://openalex.org/W3015279216","https://openalex.org/W3030116490","https://openalex.org/W3031029492","https://openalex.org/W3089228032","https://openalex.org/W3094385957","https://openalex.org/W3095263845","https://openalex.org/W3097184229","https://openalex.org/W3160972914","https://openalex.org/W3163652268","https://openalex.org/W3167537561","https://openalex.org/W3185609497","https://openalex.org/W3196582306","https://openalex.org/W3198543387","https://openalex.org/W3204428002","https://openalex.org/W3206706278","https://openalex.org/W3207237993","https://openalex.org/W4205689591","https://openalex.org/W4220911641","https://openalex.org/W4224871700","https://openalex.org/W4224929689","https://openalex.org/W4282962838","https://openalex.org/W4283031696","https://openalex.org/W4283329643","https://openalex.org/W4283727958","https://openalex.org/W4283800072","https://openalex.org/W4285309026","https://openalex.org/W4287605862","https://openalex.org/W4287645044","https://openalex.org/W4291217594","https://openalex.org/W4294891909","https://openalex.org/W4295723153","https://openalex.org/W4297841626","https://openalex.org/W4298310324","https://openalex.org/W4298642009","https://openalex.org/W4299286321","https://openalex.org/W4307210345","https://openalex.org/W4307717098","https://openalex.org/W4308504208","https://openalex.org/W4310873168","https://openalex.org/W4366549375","https://openalex.org/W4372348953","https://openalex.org/W4385245566","https://openalex.org/W4393822649","https://openalex.org/W4398958419"],"related_works":["https://openalex.org/W1991848873","https://openalex.org/W3004570917","https://openalex.org/W4389240440","https://openalex.org/W2084430325","https://openalex.org/W2041661331","https://openalex.org/W2539207221","https://openalex.org/W2045803470","https://openalex.org/W2242743481","https://openalex.org/W1571953124","https://openalex.org/W2622611424"],"abstract_inverted_index":{"Imagine":[0],"being":[1,20,33],"able":[2,21,34],"to":[3,5,22,35,115,117,169],"listen":[4],"the":[6,14,70,84,96,164,171],"birds":[7],"chirping":[8],"in":[9,56,95,150,174],"a":[10,28,46,108,137,143],"park":[11],"without":[12],"hearing":[13],"chatter":[15],"from":[16,64],"other":[17],"hikers,":[18],"or":[19,60],"block":[23],"out":[24],"traffic":[25],"noise":[26],"on":[27,142],"busy":[29],"street":[30],"while":[31,67],"still":[32],"hear":[36],"emergency":[37],"sirens":[38],"and":[39,101,104,131,154,167],"car":[40],"honks.":[41],"We":[42],"introduce":[43],"semantic":[44],"hearing,":[45],"novel":[47],"capability":[48],"for":[49],"hearable":[50],"devices":[51],"that":[52,88,111,122,132,158],"enables":[53],"them":[54],"to,":[55],"real-time,":[57],"focus":[58],"on,":[59],"ignore,":[61],"specific":[62],"sounds":[63,100,166],"real-world":[65,118],"environments,":[66],"also":[68],"preserving":[69],"spatial":[71,172],"cues.":[72],"To":[73],"achieve":[74,90],"this,":[75],"we":[76,82,106],"make":[77],"two":[78],"technical":[79],"contributions:":[80],"1)":[81],"present":[83],"first":[85],"neural":[86],"network":[87,135],"can":[89,125,162],"binaural":[91,176],"target":[92,165],"sound":[93,129],"extraction":[94],"presence":[97],"of":[98,139],"interfering":[99],"background":[102],"noise,":[103],"2)":[105],"design":[107],"training":[109],"methodology":[110],"allows":[112],"our":[113,123,133,159],"system":[114,124,161],"generalize":[116,168],"use.":[119],"Results":[120],"show":[121],"operate":[126],"with":[127,148,180],"20":[128],"classes":[130],"transformer-based":[134],"has":[136],"runtime":[138],"6.56":[140],"ms":[141],"connected":[144],"smartphone.":[145],"In-the-wild":[146],"evaluation":[147],"participants":[149],"previously":[151],"unseen":[152],"indoor":[153],"outdoor":[155],"scenarios":[156],"shows":[157],"proof-of-concept":[160],"extract":[163],"preserve":[170],"cues":[173],"its":[175],"output.":[177],"Project":[178],"page":[179],"code:":[181],"https://semantichearing.cs.washington.edu":[182]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}