{"id":"https://openalex.org/W4388755868","doi":"https://doi.org/10.1109/taslp.2023.3334101","title":"Multi-Channel Speech Separation Using Spatially Selective Deep Non-Linear Filters","display_name":"Multi-Channel Speech Separation Using Spatially Selective Deep Non-Linear Filters","publication_year":2023,"publication_date":"2023-11-17","ids":{"openalex":"https://openalex.org/W4388755868","doi":"https://doi.org/10.1109/taslp.2023.3334101"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3334101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3334101","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":3.6631,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.94367069,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"542","last_page":"553"},"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.9979000091552734,"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/separation","display_name":"Separation (statistics)","score":0.8295267820358276},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5621159076690674},{"id":"https://openalex.org/keywords/separation-method","display_name":"Separation method","score":0.4126364588737488},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4123036861419678},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.35074254870414734},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3479539453983307},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14110392332077026},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12537983059883118},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.12360122799873352},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.100404292345047},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.0625106692314148}],"concepts":[{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.8295267820358276},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5621159076690674},{"id":"https://openalex.org/C3018256011","wikidata":"https://www.wikidata.org/wiki/Q898987","display_name":"Separation method","level":2,"score":0.4126364588737488},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4123036861419678},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.35074254870414734},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3479539453983307},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14110392332077026},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12537983059883118},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.12360122799873352},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.100404292345047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0625106692314148}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3334101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3334101","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/4","display_name":"Quality Education","score":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G8974504424","display_name":"Tiefe Neuronale Netzwerke f\u00fcr die nichtlineare mehrkanalige Sprachverbesserung","funder_award_id":"508337379","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"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":47,"referenced_works":["https://openalex.org/W653761051","https://openalex.org/W1895577753","https://openalex.org/W2042860487","https://openalex.org/W2051428568","https://openalex.org/W2111937449","https://openalex.org/W2117678320","https://openalex.org/W2125768106","https://openalex.org/W2155638623","https://openalex.org/W2219249508","https://openalex.org/W2289480995","https://openalex.org/W2291877678","https://openalex.org/W2568308529","https://openalex.org/W2714509385","https://openalex.org/W2734774145","https://openalex.org/W2747306262","https://openalex.org/W2750380122","https://openalex.org/W2763188033","https://openalex.org/W2803322398","https://openalex.org/W2804228164","https://openalex.org/W2892163332","https://openalex.org/W2900893004","https://openalex.org/W2909607850","https://openalex.org/W2964058413","https://openalex.org/W2972802573","https://openalex.org/W2975955714","https://openalex.org/W3015372568","https://openalex.org/W3015791598","https://openalex.org/W3016131876","https://openalex.org/W3016257794","https://openalex.org/W3043433769","https://openalex.org/W3151596526","https://openalex.org/W3153985003","https://openalex.org/W3160140981","https://openalex.org/W4214498238","https://openalex.org/W4223583411","https://openalex.org/W4225302959","https://openalex.org/W4229371942","https://openalex.org/W4296068418","https://openalex.org/W4297841581","https://openalex.org/W4310337937","https://openalex.org/W4312219134","https://openalex.org/W4372267870","https://openalex.org/W4372347386","https://openalex.org/W4375868926","https://openalex.org/W6631190155","https://openalex.org/W6688816777","https://openalex.org/W6784139575"],"related_works":["https://openalex.org/W2791440692","https://openalex.org/W2361398959","https://openalex.org/W2693899803","https://openalex.org/W2384308427","https://openalex.org/W2056729981","https://openalex.org/W1593372860","https://openalex.org/W1509352139","https://openalex.org/W235709208","https://openalex.org/W155145594","https://openalex.org/W2944352181"],"abstract_inverted_index":{"In":[0,19],"a":[1,48,65,75,98,113,141,145,169,202],"multi-channel":[2,35,66],"separation":[3,51,68,117],"task":[4],"with":[5,103,112,148,198],"multiple":[6],"speakers,":[7],"we":[8,73,177],"aim":[9],"to":[10,21,90,131,168,185,196],"recover":[11],"all":[12],"individual":[13],"speech":[14,33],"signals":[15],"from":[16],"the":[17,27,32,40,45,54,61,92,104,109,138,149,162,173,180],"mixture.":[18],"contrast":[20],"single-channel":[22],"approaches,":[23],"which":[24,127,164],"rely":[25],"on":[26],"different":[28,41],"spectro-temporal":[29],"characteristics":[30],"of":[31,44,56,94,172],"signals,":[34],"approaches":[36],"should":[37],"additionally":[38],"utilize":[39],"spatial":[42,62,133,174],"locations":[43],"sources":[46,57,188],"for":[47],"more":[49,157],"powerful":[50],"especially":[52],"when":[53,154],"number":[55],"increases.":[58],"To":[59],"enhance":[60],"processing":[63],"in":[64,70,161],"source":[67],"scenario,":[69],"this":[71],"work,":[72],"propose":[74],"deep":[76],"neural":[77,100],"network":[78,101,152],"(DNN)":[79],"based":[80],"spatially":[81,88],"selective":[82],"filter":[83],"(SSF)":[84],"that":[85,137,179,189],"can":[86,165],"be":[87,166],"steered":[89],"extract":[91],"speaker":[93],"interest":[95],"by":[96],"initializing":[97],"recurrent":[99],"layer":[102],"target":[105],"direction.":[106],"We":[107,135],"compare":[108],"proposed":[110],"SSF":[111,139,181],"common":[114],"end-to-end":[115],"direct":[116],"(DS)":[118],"approach":[119,147],"trained":[120],"using":[121],"utterance-wise":[122],"permutation":[123],"invariant":[124],"training":[125,194],"(PIT),":[126],"only":[128],"implicitly":[129],"learns":[130],"perform":[132],"filtering.":[134],"show":[136],"has":[140],"clear":[142],"advantage":[143],"over":[144],"DS":[146],"same":[150],"underlying":[151],"architecture":[153],"there":[155],"are":[156],"than":[158],"two":[159],"speakers":[160,199],"mixture,":[163],"attributed":[167],"better":[170,184],"use":[171],"information.":[175],"Furthermore,":[176],"find":[178],"generalizes":[182],"much":[183],"additional":[186],"noise":[187],"were":[190],"not":[191],"seen":[192],"during":[193],"and":[195],"scenarios":[197],"positioned":[200],"at":[201],"similar":[203],"angle.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":7}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2023-11-18T00:00:00"}