{"id":"https://openalex.org/W4396833001","doi":"https://doi.org/10.1145/3613904.3642057","title":"Look Once to Hear: Target Speech Hearing with Noisy Examples","display_name":"Look Once to Hear: Target Speech Hearing with Noisy Examples","publication_year":2024,"publication_date":"2024-05-11","ids":{"openalex":"https://openalex.org/W4396833001","doi":"https://doi.org/10.1145/3613904.3642057"},"language":"en","primary_location":{"id":"doi:10.1145/3613904.3642057","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613904.3642057","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613904.3642057","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 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3613904.3642057","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/A5091414943","display_name":"Tuochao Chen","orcid":"https://orcid.org/0000-0002-8031-5066"},"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":"Tuochao Chen","raw_affiliation_strings":["Paul G. Allen Center for Computer Science and Engineering, University of Washington, United States"],"raw_orcid":"https://orcid.org/0000-0002-8031-5066","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/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":["AssemblyAI, United States and Microsoft, United States"],"raw_orcid":"https://orcid.org/0009-0003-7791-3545","affiliations":[{"raw_affiliation_string":"AssemblyAI, United States and 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":["Paul G. Allen Center for Computer Science and Engineering, University of Washington, United States"],"raw_orcid":"https://orcid.org/0000-0002-9863-3054","affiliations":[{"raw_affiliation_string":"Paul G. Allen Center for Computer Science and Engineering, 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":7.0316,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.97790026,"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":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9972000122070312,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/speech-recognition","display_name":"Speech recognition","score":0.6636244058609009},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6432259678840637},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.412159264087677},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.348688006401062},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.05492216348648071}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6636244058609009},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6432259678840637},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.412159264087677},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.348688006401062},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.05492216348648071}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3613904.3642057","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613904.3642057","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613904.3642057","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 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.06289","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.06289","pdf_url":"https://arxiv.org/pdf/2405.06289","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3613904.3642057","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613904.3642057","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613904.3642057","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 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396833001.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2032191478","https://openalex.org/W2077856040","https://openalex.org/W2108668360","https://openalex.org/W2129934596","https://openalex.org/W2162654459","https://openalex.org/W2167734090","https://openalex.org/W2503663328","https://openalex.org/W2680270903","https://openalex.org/W2749510669","https://openalex.org/W2765654763","https://openalex.org/W2877975652","https://openalex.org/W2900292050","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2962960500","https://openalex.org/W2972513594","https://openalex.org/W2972541922","https://openalex.org/W2972568703","https://openalex.org/W2972802573","https://openalex.org/W2973062255","https://openalex.org/W2995181338","https://openalex.org/W3011424113","https://openalex.org/W3015199127","https://openalex.org/W3015279216","https://openalex.org/W3034577429","https://openalex.org/W3095717210","https://openalex.org/W3096408984","https://openalex.org/W3148386121","https://openalex.org/W3162879334","https://openalex.org/W3163346546","https://openalex.org/W3198543387","https://openalex.org/W3205770165","https://openalex.org/W3205878676","https://openalex.org/W3206706278","https://openalex.org/W4225905067","https://openalex.org/W4282962838","https://openalex.org/W4283800072","https://openalex.org/W4289665794","https://openalex.org/W4302446929","https://openalex.org/W4320930770","https://openalex.org/W4367597591","https://openalex.org/W4372348953","https://openalex.org/W4375868849","https://openalex.org/W4379769651","https://openalex.org/W4387835382"],"related_works":["https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"In":[0],"crowded":[1],"settings,":[2],"the":[3,44,59,69,92,97,101,118,133,226],"human":[4,227],"brain":[5],"can":[6,160],"focus":[7],"on":[8,170],"speech":[9,34,40,55,130],"from":[10],"a":[11,23,53,75,85,105,110,143,215],"target":[12,33,45,60,102,119],"speaker,":[13],"given":[14],"prior":[15],"knowledge":[16],"of":[17,117,135,147,155,164],"how":[18],"they":[19],"sound.":[20],"We":[21,90],"introduce":[22],"novel":[24],"intelligent":[25],"hearable":[26,70],"system":[27,141],"that":[28],"achieves":[29,142],"this":[30,218],"capability,":[31],"enabling":[32],"hearing":[35],"to":[36,51,57,108,179,206],"ignore":[37],"all":[38],"interfering":[39,136],"and":[41,128,138,159,182,189,212],"noise,":[42],"but":[43],"speaker.":[46,61,120],"A":[47],"na\u00efve":[48],"approach":[49],"is":[50,63,78,124],"require":[52],"clean":[54,76,207],"example":[56,77,116,123],"enroll":[58],"This":[62,121],"however":[64],"not":[65,201],"well":[66],"aligned":[67],"with":[68,230],"application":[71],"domain":[72],"since":[73],"obtaining":[74],"challenging":[79],"in":[80,132,167,185],"real":[81],"world":[82],"scenarios,":[83],"creating":[84],"unique":[86],"user":[87,175],"interface":[88,95,196],"problem.":[89],"present":[91],"first":[93],"enrollment":[94,127,157,195],"where":[96],"wearer":[98],"looks":[99],"at":[100],"speaker":[103],"for":[104,126,197],"few":[106],"seconds":[107,154],"capture":[109],"single,":[111],"short,":[112],"highly":[113],"noisy,":[114],"binaural":[115],"noisy":[122,156,198],"used":[125],"subsequent":[129],"extraction":[131],"presence":[134],"speakers":[137,184],"noise.":[139],"Our":[140,174],"signal":[144],"quality":[145],"improvement":[146],"7.01":[148],"dB":[149],"using":[150],"less":[151],"than":[152],"5":[153],"audio":[158,165],"process":[161],"8":[162],"ms":[163,169],"chunks":[166],"6.24":[168],"an":[171,221],"embedded":[172],"CPU.":[173],"studies":[176],"demonstrate":[177],"generalization":[178],"real-world":[180],"static":[181],"mobile":[183],"previously":[186],"unseen":[187],"indoor":[188],"outdoor":[190],"multipath":[191],"environments.":[192],"Finally,":[193],"our":[194],"examples":[199],"does":[200],"cause":[202],"performance":[203],"degradation":[204],"compared":[205],"examples,":[208],"while":[209],"being":[210],"convenient":[211],"user-friendly.":[213],"Taking":[214],"step":[216,223],"back,":[217],"paper":[219],"takes":[220],"important":[222],"towards":[224],"enhancing":[225],"auditory":[228],"perception":[229],"artificial":[231],"intelligence.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}