{"id":"https://openalex.org/W4416250701","doi":"https://doi.org/10.1109/waspaa66052.2025.11230948","title":"Self-Steering Deep Non-Linear Spatially Selective Filters for Efficient Extraction of Moving Speakers under Weak Guidance","display_name":"Self-Steering Deep Non-Linear Spatially Selective Filters for Efficient Extraction of Moving Speakers under Weak Guidance","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416250701","doi":"https://doi.org/10.1109/waspaa66052.2025.11230948"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230948","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":"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/A5114619460","display_name":"Jakob Kienegger","orcid":null},"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":true,"raw_author_name":"Jakob Kienegger","raw_affiliation_strings":["University of Hamburg,Germany"],"affiliations":[{"raw_affiliation_string":"University of Hamburg,Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107744399","display_name":"Alina Mannanova","orcid":null},"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":"Alina Mannanova","raw_affiliation_strings":["University of Hamburg,Germany"],"affiliations":[{"raw_affiliation_string":"University of Hamburg,Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011728435","display_name":"Huajian Fang","orcid":null},"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":"Huajian Fang","raw_affiliation_strings":["University of Hamburg,Germany"],"affiliations":[{"raw_affiliation_string":"University of Hamburg,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":["University of Hamburg,Germany"],"affiliations":[{"raw_affiliation_string":"University of Hamburg,Germany","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5114619460"],"corresponding_institution_ids":["https://openalex.org/I159176309"],"apc_list":null,"apc_paid":null,"fwci":1.2783,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84935504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"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":0.9886000156402588,"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":0.9886000156402588,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.003700000001117587,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.001500000013038516,"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/leverage","display_name":"Leverage (statistics)","score":0.6121000051498413},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5605999827384949},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5253999829292297},{"id":"https://openalex.org/keywords/particle-filter","display_name":"Particle filter","score":0.512499988079071},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.49639999866485596},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4708999991416931},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.41920000314712524},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.37790000438690186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7160000205039978},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6121000051498413},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5605999827384949},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5253999829292297},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.512499988079071},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.49639999866485596},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4708999991416931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43639999628067017},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.41920000314712524},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40869998931884766},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38909998536109924},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.375},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.29760000109672546},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C121475858","wikidata":"https://www.wikidata.org/wiki/Q2735911","display_name":"Spatial filter","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C22597639","wikidata":"https://www.wikidata.org/wiki/Q5449227","display_name":"Filter design","level":3,"score":0.2687000036239624},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.26269999146461487},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2565999925136566},{"id":"https://openalex.org/C102248274","wikidata":"https://www.wikidata.org/wiki/Q168388","display_name":"Adaptive filter","level":2,"score":0.2517000138759613},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230948","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1483307070","https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1648602279","https://openalex.org/W2001899073","https://openalex.org/W2030486566","https://openalex.org/W2039969836","https://openalex.org/W2062474264","https://openalex.org/W2090629256","https://openalex.org/W2098613108","https://openalex.org/W2107493093","https://openalex.org/W2117678320","https://openalex.org/W2123993331","https://openalex.org/W2140242774","https://openalex.org/W2160337655","https://openalex.org/W2884797218","https://openalex.org/W2889442120","https://openalex.org/W2898268964","https://openalex.org/W2952218014","https://openalex.org/W3002906933","https://openalex.org/W3016232124","https://openalex.org/W3088309240","https://openalex.org/W3097945073","https://openalex.org/W3160129476","https://openalex.org/W3196556869","https://openalex.org/W4296068418","https://openalex.org/W4312219134","https://openalex.org/W4367597591","https://openalex.org/W4372269199","https://openalex.org/W4372347386","https://openalex.org/W4375869077","https://openalex.org/W4385822249","https://openalex.org/W4388755868","https://openalex.org/W4389776368","https://openalex.org/W4392908923","https://openalex.org/W4395471087","https://openalex.org/W4402112351","https://openalex.org/W4402112488","https://openalex.org/W4403126366","https://openalex.org/W4403126980","https://openalex.org/W4404577147","https://openalex.org/W4406461266","https://openalex.org/W4408352326","https://openalex.org/W4415433228"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"works":[1],"on":[2,42,116],"deep":[3],"non-linear":[4],"spatially":[5,101],"selective":[6,102],"filters":[7],"demonstrate":[8],"exceptional":[9],"enhancement":[10,136],"performance":[11,26],"with":[12,141],"computationally":[13],"lightweight":[14],"architectures":[15],"for":[16,106],"stationary":[17],"speakers":[18],"of":[19,46,78,99,111],"known":[20],"directions.":[21],"However,":[22],"to":[23,36,93,104,134],"maintain":[24],"this":[25,51],"in":[27,57,75],"dynamic":[28],"scenarios,":[29],"resource-intensive":[30],"data-driven":[31],"tracking":[32,73,130],"algorithms":[33,127],"become":[34],"necessary":[35],"provide":[37],"precise":[38],"spatial":[39],"guidance":[40],"conditioned":[41],"the":[43,76,95,100,107,112,122],"initial":[44],"direction":[45],"a":[47,67,71,79,84,117,149],"target":[48],"speaker.":[49],"As":[50],"additional":[52],"computational":[53],"overhead":[54],"hinders":[55],"application":[56],"resource-constrained":[58],"scenarios":[59],"such":[60],"as":[61,157],"real-time":[62],"speech":[63,97],"enhancement,":[64],"we":[65,89],"present":[66],"novel":[68],"strategy":[69],"utilizing":[70],"low-complexity":[72],"algorithm":[74],"form":[77],"particle":[80,113],"filter":[81,103],"instead.":[82],"Assuming":[83],"causal,":[85],"sequential":[86],"processing":[87],"style,":[88],"introduce":[90],"temporal":[91],"feedback":[92],"leverage":[94],"enhanced":[96],"signal":[98],"compensate":[105],"limited":[108],"modeling":[109],"capabilities":[110],"filter.":[114],"Evaluation":[115],"synthetic":[118],"dataset":[119],"illustrates":[120],"how":[121],"autoregressive":[123],"interplay":[124],"between":[125],"both":[126],"drastically":[128],"improves":[129],"accuracy":[131],"and":[132],"leads":[133],"strong":[135],"performance.":[137],"A":[138],"listening":[139],"test":[140],"real-world":[142],"recordings":[143],"complements":[144],"these":[145],"findings":[146],"by":[147],"indicating":[148],"clear":[150],"trend":[151],"towards":[152],"our":[153],"proposed":[154],"self-steering":[155],"pipeline":[156],"preferred":[158],"choice":[159],"over":[160],"comparable":[161],"methods.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-11-14T00:00:00"}