{"id":"https://openalex.org/W4372347386","doi":"https://doi.org/10.1109/icassp49357.2023.10096098","title":"Spatially Selective Deep Non-Linear Filters For Speaker Extraction","display_name":"Spatially Selective Deep Non-Linear Filters For Speaker Extraction","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372347386","doi":"https://doi.org/10.1109/icassp49357.2023.10096098"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5073497010","display_name":"Kristina Tesch","orcid":"https://orcid.org/0000-0002-6458-8128"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kristina Tesch","raw_affiliation_strings":["Universit&#x00E4;t Hamburg,Signal Processing (SP),Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E4;t Hamburg,Signal Processing (SP),Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087022569","display_name":"Timo Gerkmann","orcid":"https://orcid.org/0000-0002-8678-4699"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Timo Gerkmann","raw_affiliation_strings":["Universit&#x00E4;t Hamburg,Signal Processing (SP),Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E4;t Hamburg,Signal Processing (SP),Germany","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.88,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.94620527,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"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":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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.7251659035682678},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.6767936944961548},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5355503559112549},{"id":"https://openalex.org/keywords/spatial-filter","display_name":"Spatial filter","score":0.49227872490882874},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4859005808830261},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.47986096143722534},{"id":"https://openalex.org/keywords/linear-filter","display_name":"Linear filter","score":0.4770599901676178},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.473757803440094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4729166626930237},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46823400259017944},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.440518856048584},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4282700717449188},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3664637506008148},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2239147424697876},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19147393107414246},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0804099440574646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7251659035682678},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.6767936944961548},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5355503559112549},{"id":"https://openalex.org/C121475858","wikidata":"https://www.wikidata.org/wiki/Q2735911","display_name":"Spatial filter","level":2,"score":0.49227872490882874},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4859005808830261},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.47986096143722534},{"id":"https://openalex.org/C139722471","wikidata":"https://www.wikidata.org/wiki/Q2619517","display_name":"Linear filter","level":3,"score":0.4770599901676178},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.473757803440094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4729166626930237},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46823400259017944},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.440518856048584},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4282700717449188},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3664637506008148},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2239147424697876},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19147393107414246},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0804099440574646},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W126779258","https://openalex.org/W1522301498","https://openalex.org/W1895577753","https://openalex.org/W2051428568","https://openalex.org/W2106272332","https://openalex.org/W2117678320","https://openalex.org/W2289480995","https://openalex.org/W2291877678","https://openalex.org/W2398972335","https://openalex.org/W2763188033","https://openalex.org/W2891833136","https://openalex.org/W2892163332","https://openalex.org/W2900893004","https://openalex.org/W2909607850","https://openalex.org/W2964171275","https://openalex.org/W2972802573","https://openalex.org/W2973062255","https://openalex.org/W2975955714","https://openalex.org/W2990433241","https://openalex.org/W3015791598","https://openalex.org/W3092796334","https://openalex.org/W3136499730","https://openalex.org/W3153985003","https://openalex.org/W3157899172","https://openalex.org/W3158652463","https://openalex.org/W3192281612","https://openalex.org/W3196940724","https://openalex.org/W4210402803","https://openalex.org/W4214498238","https://openalex.org/W4296068418","https://openalex.org/W4297841581","https://openalex.org/W4312219134","https://openalex.org/W6605165268","https://openalex.org/W6631190155","https://openalex.org/W6770796734","https://openalex.org/W6784139575"],"related_works":["https://openalex.org/W4230814943","https://openalex.org/W2035463881","https://openalex.org/W2105387367","https://openalex.org/W2937498565","https://openalex.org/W1970684742","https://openalex.org/W1989456320","https://openalex.org/W1986200848","https://openalex.org/W2016543325","https://openalex.org/W2027252085","https://openalex.org/W2561203620"],"abstract_inverted_index":{"In":[0,24],"a":[1,29,48],"scenario":[2],"with":[3],"multiple":[4],"persons":[5],"talking":[6],"simultaneously,":[7],"the":[8,12,15,21,56,60,66,78,83,86],"spatial":[9],"characteristics":[10],"of":[11,59,85,105,109],"signals":[13],"are":[14],"most":[16],"distinct":[17],"feature":[18],"for":[19,102],"extracting":[20],"target":[22,42,67],"signal.":[23],"this":[25,45,72,121],"work,":[26],"we":[27,46,118],"develop":[28],"deep":[30],"joint":[31],"spatial-spectral":[32],"non-linear":[33,96],"filter":[34,87],"that":[35,71],"can":[36,98],"be":[37,100],"steered":[38],"to":[39],"an":[40,106],"arbitrary":[41,107],"direction.":[43,68],"For":[44],"propose":[47],"simple":[49],"and":[50,81,111],"effective":[51,76],"conditioning":[52],"mechanism,":[53],"which":[54],"sets":[55],"initial":[57],"state":[58],"filter\u2019s":[61],"recurrent":[62],"layers":[63],"based":[64],"on":[65],"We":[69],"show":[70],"scheme":[73],"is":[74],"more":[75],"than":[77],"baseline":[79],"approach":[80],"increases":[82],"flexibility":[84],"at":[88],"no":[89],"performance":[90],"cost.":[91],"The":[92],"resulting":[93],"spatially":[94],"selective":[95],"filters":[97],"also":[99],"used":[101],"speech":[103],"separation":[104],"number":[108],"speakers":[110],"enable":[112],"very":[113],"accurate":[114],"multi-speaker":[115],"localization":[116],"as":[117],"demonstrate":[119],"in":[120],"paper.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
