{"id":"https://openalex.org/W4312219134","doi":"https://doi.org/10.1109/taslp.2022.3221046","title":"Insights Into Deep Non-Linear Filters for Improved Multi-Channel Speech Enhancement","display_name":"Insights Into Deep Non-Linear Filters for Improved Multi-Channel Speech Enhancement","publication_year":2022,"publication_date":"2022-11-10","ids":{"openalex":"https://openalex.org/W4312219134","doi":"https://doi.org/10.1109/taslp.2022.3221046"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3221046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3221046","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kristina Tesch","raw_affiliation_strings":["Signal Processing Group, Department of Informatics, Universität Hamburg, Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6458-8128","affiliations":[{"raw_affiliation_string":"Signal Processing Group, Department of Informatics, Universität Hamburg, Hamburg, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087022569","display_name":"Timo Gerkmann","orcid":"https://orcid.org/0000-0002-8678-4699"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Timo Gerkmann","raw_affiliation_strings":["Signal Processing Group, Department of Informatics, Universität Hamburg, Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8678-4699","affiliations":[{"raw_affiliation_string":"Signal Processing Group, Department of Informatics, Universität Hamburg, Hamburg, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.6622,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":{"value":0.98924552,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"563","last_page":"575"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.998199999332428,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9932000041007996,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.778695821762085},{"id":"https://openalex.org/keywords/spatial-filter","display_name":"Spatial filter","score":0.7068402171134949},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.5677860975265503},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.537883996963501},{"id":"https://openalex.org/keywords/linear-filter","display_name":"Linear filter","score":0.49078425765037537},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47640979290008545},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.47466233372688293},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.459448903799057},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4565006196498871},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44525885581970215},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.4161864221096039},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39149636030197144},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12637531757354736},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10926693677902222},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10348087549209595}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.778695821762085},{"id":"https://openalex.org/C121475858","wikidata":"https://www.wikidata.org/wiki/Q2735911","display_name":"Spatial filter","level":2,"score":0.7068402171134949},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.5677860975265503},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.537883996963501},{"id":"https://openalex.org/C139722471","wikidata":"https://www.wikidata.org/wiki/Q2619517","display_name":"Linear filter","level":3,"score":0.49078425765037537},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47640979290008545},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.47466233372688293},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.459448903799057},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4565006196498871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44525885581970215},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.4161864221096039},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39149636030197144},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12637531757354736},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10926693677902222},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10348087549209595},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3221046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3221046","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4399999976158142,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1544785557","https://openalex.org/W1584645830","https://openalex.org/W1931312565","https://openalex.org/W2064675550","https://openalex.org/W2106272332","https://openalex.org/W2109215269","https://openalex.org/W2117678320","https://openalex.org/W2130476329","https://openalex.org/W2141783538","https://openalex.org/W2289394825","https://openalex.org/W2289480995","https://openalex.org/W2291877678","https://openalex.org/W2398972335","https://openalex.org/W2515728195","https://openalex.org/W2516001803","https://openalex.org/W2714509385","https://openalex.org/W2763188033","https://openalex.org/W2791686384","https://openalex.org/W2889442120","https://openalex.org/W2890489755","https://openalex.org/W2892163332","https://openalex.org/W2900893004","https://openalex.org/W2937235446","https://openalex.org/W2945191446","https://openalex.org/W2972802573","https://openalex.org/W2972847427","https://openalex.org/W2972992323","https://openalex.org/W2975955714","https://openalex.org/W2990433241","https://openalex.org/W2998678989","https://openalex.org/W3004309045","https://openalex.org/W3009032512","https://openalex.org/W3015372568","https://openalex.org/W3015791598","https://openalex.org/W3032514799","https://openalex.org/W3147539069","https://openalex.org/W3153985003","https://openalex.org/W3160085755","https://openalex.org/W3162341667","https://openalex.org/W3177067699","https://openalex.org/W3192281612","https://openalex.org/W3196360884","https://openalex.org/W3196940724","https://openalex.org/W3205004157","https://openalex.org/W4210402803","https://openalex.org/W4214498238","https://openalex.org/W4225604170","https://openalex.org/W4296068418","https://openalex.org/W6631190155","https://openalex.org/W6770796734","https://openalex.org/W6804452642"],"related_works":["https://openalex.org/W4234307581","https://openalex.org/W4230814943","https://openalex.org/W2035463881","https://openalex.org/W3126337586","https://openalex.org/W2105387367","https://openalex.org/W2937498565","https://openalex.org/W1970684742","https://openalex.org/W1989456320","https://openalex.org/W1986200848","https://openalex.org/W2016543325"],"abstract_inverted_index":{"The":[0],"key":[1],"advantage":[2],"of":[3,60,67,71,89,109,146,169,196],"using":[4],"multiple":[5],"microphones":[6,170],"for":[7,93,165],"speech":[8,95],"enhancement":[9,96],"is":[10,40],"that":[11,57,66,84,178,209],"spatial":[12,27,50,72,112,149,157,188,194],"filtering":[13,28],"can":[14,76],"be":[15,78,184],"used":[16],"to":[17,46,86,139,204],"complement":[18],"the":[19,58,81,107,131,140,144,193,197,229],"tempo-spectral":[20,52,74],"processing.":[21],"In":[22,37],"a":[23,41,48,61,68,110,116,147,160,166,205,215],"traditional":[24],"setting,":[25],"linear":[26,62,156],"(beamforming)":[29],"and":[30,51,65,73,125,136,223],"single-channel":[31],"post-filtering":[32],"are":[33,97],"commonly":[34],"performed":[35],"separately.":[36],"contrast,":[38],"there":[39],"trend":[42],"towards":[43],"employing":[44],"(DNNs)":[45],"learn":[47],"joint":[49],"non-linear":[53,111,148],"filter,":[54],"which":[55,152],"means":[56],"restriction":[59],"processing":[63,70,127,150],"model":[64],"separate":[69],"information":[75,132,182,189],"potentially":[77],"overcome.":[79],"However,":[80],"internal":[82],"mechanisms":[83],"lead":[85],"good":[87],"performance":[88],"such":[90],"data-driven":[91],"filters":[92],"multi-channel":[94],"not":[98],"well":[99,119],"understood.":[100],"Therefore,":[101],"in":[102,159,179],"this":[103,191],"work,":[104],"we":[105],"analyse":[106],"properties":[108],"filter":[113,158],"realized":[114],"by":[115,128,171,219,224],"DNN":[117],"as":[118,120,190],"its":[121],"interdependency":[122],"with":[123,187],"temporal":[124],"spectral":[126,181],"carefully":[129],"controlling":[130],"sources":[133],"(spatial,":[134],"spectral,":[135],"temporal)":[137],"available":[138],"network.":[141],"We":[142],"confirm":[143],"superiority":[145],"model,":[151],"outperforms":[153,210],"an":[154],"oracle":[155],"challenging":[161],"speaker":[162,216],"extraction":[163,217],"scenario":[164],"low":[167],"number":[168],"0.24":[172],"POLQA":[173,221,226],"score.":[174],"Our":[175,199],"analyses":[176],"reveal":[177],"particular":[180],"should":[183],"processed":[185],"jointly":[186],"increases":[192],"selectivity":[195],"filter.":[198],"systematic":[200],"evaluation":[201],"then":[202],"leads":[203],"simple":[206],"network":[207,212],"architecture,":[208],"state-of-the-art":[211],"architectures":[213],"on":[214,228],"task":[218],"0.22":[220],"score":[222,227],"0.32":[225],"CHiME3":[230],"data.":[231]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":26},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}