{"id":"https://openalex.org/W4296070366","doi":"https://doi.org/10.21437/interspeech.2022-11100","title":"Distance-Based Sound Separation","display_name":"Distance-Based Sound Separation","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296070366","doi":"https://doi.org/10.21437/interspeech.2022-11100"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11100","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11100","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"article","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/A5051479650","display_name":"Katharine Patterson","orcid":"https://orcid.org/0000-0002-7116-6169"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Katharine Patterson","raw_affiliation_strings":["Google Research, Cambridge MA"],"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge MA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069301909","display_name":"Kevin R. Wilson","orcid":"https://orcid.org/0000-0003-0264-0872"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Wilson","raw_affiliation_strings":["Google Research, Cambridge MA"],"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge MA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053447215","display_name":"Scott Wisdom","orcid":"https://orcid.org/0000-0001-6671-1428"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Wisdom","raw_affiliation_strings":["Google Research, Cambridge MA"],"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge MA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["Google Research, Cambridge MA"],"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge MA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051479650"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":2.7949,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.93075228,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"901","last_page":"905"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.996999979019165,"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":0.996999979019165,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9807000160217285,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.95660001039505,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.7032699584960938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5339905619621277},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5056121349334717},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.407283216714859},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13491863012313843},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.06968837976455688}],"concepts":[{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.7032699584960938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5339905619621277},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5056121349334717},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.407283216714859},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13491863012313843},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.06968837976455688}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11100","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11100","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W187699606","https://openalex.org/W1494198834","https://openalex.org/W1512817138","https://openalex.org/W1522301498","https://openalex.org/W1569053397","https://openalex.org/W2020502910","https://openalex.org/W2105592556","https://openalex.org/W2117678320","https://openalex.org/W2135823751","https://openalex.org/W2136017566","https://openalex.org/W2151981731","https://openalex.org/W2173474324","https://openalex.org/W2889540509","https://openalex.org/W2900429685","https://openalex.org/W2916618641","https://openalex.org/W2938515563","https://openalex.org/W2952350176","https://openalex.org/W2962708126","https://openalex.org/W2963189033","https://openalex.org/W2963941778","https://openalex.org/W2964058413","https://openalex.org/W2982059757","https://openalex.org/W2995181338","https://openalex.org/W2997297221","https://openalex.org/W3004910802","https://openalex.org/W3020804303","https://openalex.org/W3028019732","https://openalex.org/W3123318516","https://openalex.org/W3151596526","https://openalex.org/W3168140565","https://openalex.org/W3186050523"],"related_works":["https://openalex.org/W4211182446","https://openalex.org/W4245868110","https://openalex.org/W4252487970","https://openalex.org/W4255839737","https://openalex.org/W4240941274","https://openalex.org/W2775902113","https://openalex.org/W1971118083","https://openalex.org/W4233773735","https://openalex.org/W4255037941","https://openalex.org/W4235181573"],"abstract_inverted_index":{"We":[0],"propose":[1],"the":[2,22,42,54,83,97],"novel":[3],"task":[4],"of":[5,24,56],"distance-based":[6],"sound":[7,34],"separation,":[8],"where":[9],"sounds":[10,47,67,70,110],"are":[11],"separated":[12],"based":[13],"only":[14],"on":[15,46],"their":[16],"distance":[17,81],"from":[18,68],"a":[19,30,50,61,79,89],"single":[20,72,90],"microphone.In":[21],"context":[23],"assisted":[25],"listening":[26],"devices,":[27],"proximity":[28],"provides":[29],"simple":[31],"criterion":[32],"for":[33,108,114],"selection":[35],"in":[36,71],"noisy":[37],"environments":[38],"that":[39],"would":[40],"allow":[41],"user":[43],"to":[44,49,64,78,102],"focus":[45],"relevant":[48],"local":[51],"conversation.We":[52],"demonstrate":[53],"feasibility":[55],"this":[57],"approach":[58],"by":[59,105],"training":[60],"neural":[62],"network":[63],"separate":[65],"near":[66,86,109],"far":[69,115],"channel":[73],"synthetic":[74],"reverberant":[75],"mixtures,":[76],"relative":[77],"threshold":[80],"defining":[82],"boundary":[84],"between":[85],"and":[87,93,111],"far.With":[88],"nearby":[91],"speaker":[92],"four":[94],"distant":[95],"speakers,":[96],"model":[98],"improves":[99],"scale-invariant":[100],"signal":[101],"noise":[103],"ratio":[104],"4.4":[106],"dB":[107,113],"6.8":[112],"sounds.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-12T06:05:19.336698","created_date":"2025-10-10T00:00:00"}