{"id":"https://openalex.org/W2889755093","doi":"https://doi.org/10.1109/icassp.2018.8461336","title":"Dual Frequency- and Block-Permutation Alignment for Deep Learning Based Block-Online Blind Source Separation","display_name":"Dual Frequency- and Block-Permutation Alignment for Deep Learning Based Block-Online Blind Source Separation","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2889755093","doi":"https://doi.org/10.1109/icassp.2018.8461336","mag":"2889755093"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461336","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461336","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5011191228","display_name":"Lukas Drude","orcid":"https://orcid.org/0000-0003-3683-5432"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lukas Drude","raw_affiliation_strings":["Department of Communications Engineering, Paderborn University, Paderborn, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Communications Engineering, Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101768343","display_name":"Takuya Higuchi","orcid":"https://orcid.org/0000-0002-0361-7132"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Higuchi","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":["Department of Communications Engineering, Paderborn University, Paderborn, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Communications Engineering, Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"615","issue":null,"first_page":"691","last_page":"695"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9990000128746033,"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":0.9984999895095825,"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":0.7497809529304504},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6787710189819336},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.6266028881072998},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.6104736328125},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5401424765586853},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5132756233215332},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.40737369656562805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36707085371017456},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3295050859451294},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14962902665138245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7497809529304504},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6787710189819336},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.6266028881072998},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.6104736328125},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5401424765586853},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5132756233215332},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.40737369656562805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36707085371017456},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3295050859451294},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14962902665138245},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461336","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461336","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W285277413","https://openalex.org/W1496522993","https://openalex.org/W1686266550","https://openalex.org/W1987906574","https://openalex.org/W1996837089","https://openalex.org/W2003203076","https://openalex.org/W2012910847","https://openalex.org/W2031583051","https://openalex.org/W2039844283","https://openalex.org/W2043216213","https://openalex.org/W2117332620","https://openalex.org/W2117678320","https://openalex.org/W2127851351","https://openalex.org/W2154070811","https://openalex.org/W2158143227","https://openalex.org/W2221409856","https://openalex.org/W2289480995","https://openalex.org/W2400339399","https://openalex.org/W2408744528","https://openalex.org/W2558649592","https://openalex.org/W2567948266","https://openalex.org/W2568308529","https://openalex.org/W2591810467","https://openalex.org/W2702006285","https://openalex.org/W2750380122","https://openalex.org/W6629802697","https://openalex.org/W6649486296","https://openalex.org/W6661582794","https://openalex.org/W6677083428","https://openalex.org/W6713176261","https://openalex.org/W6739644732"],"related_works":["https://openalex.org/W2383482627","https://openalex.org/W2392054573","https://openalex.org/W2162758065","https://openalex.org/W2186864281","https://openalex.org/W2997589526","https://openalex.org/W4289145503","https://openalex.org/W2099940608","https://openalex.org/W2889447638","https://openalex.org/W2166132814","https://openalex.org/W1005611038"],"abstract_inverted_index":{"Deep":[0],"attractor":[1],"networks":[2,25],"(DANs)":[3],"are":[4],"a":[5,17,45,88,93,110,149,153,160],"recently":[6],"introduced":[7],"method":[8],"to":[9,28,40,71,80,173],"blindly":[10],"separate":[11],"sources":[12],"from":[13],"spectral":[14,69,89],"features":[15,70],"of":[16,31,53,66,118,131,171],"monaural":[18],"recording":[19],"using":[20],"bidirectional":[21],"long":[22],"short-term":[23],"memory":[24],"(BLSTMs).":[26],"Due":[27],"the":[29,51,63,73,119,139,143],"nature":[30],"BLSTMs,":[32],"this":[33],"is":[34,122],"inherently":[35],"not":[36],"online-ready":[37],"and":[38,68,77,107,142,158],"resorting":[39],"operating":[41],"on":[42,124],"blocks":[43],"yields":[44],"block":[46,74,166],"permutation":[47,75,156,167],"problem":[48,76],"in":[49,104,169],"that":[50,137],"index":[52],"each":[54],"speaker":[55],"may":[56],"change":[57],"between":[58],"blocks.":[59],"We":[60,98,135],"here":[61],"propose":[62,109],"joint":[64,102],"modeling":[65],"spatial":[67],"solve":[72],"generalize":[78],"DANs":[79],"multi-channel":[81,132],"meeting":[82],"recordings:":[83],"The":[84,116],"DAN":[85],"acts":[86],"as":[87],"feature":[90],"extractor":[91],"for":[92],"subsequent":[94],"model-based":[95],"clustering":[96],"approach.":[97],"first":[99],"analyze":[100],"different":[101],"models":[103,121],"batch-processing":[105,141],"scenarios":[106],"finally":[108],"block-online":[111,145],"blind":[112],"source":[113],"separation":[114],"algorithm.":[115],"efficacy":[117],"proposed":[120,140,144],"demonstrated":[123],"reverberant":[125],"mixtures":[126],"corrupted":[127],"by":[128],"real":[129],"recordings":[130],"background":[133],"noise.":[134],"demonstrate":[136],"both":[138],"system":[146],"outperform":[147],"(a)":[148],"spatial-only":[150],"model":[151,162],"with":[152,163],"state-of-the-art":[154],"frequency":[155],"solver":[157,168],"(b)":[159],"spectral-only":[161],"an":[164],"oracle":[165],"terms":[170],"signal":[172],"distortion":[174],"ratio":[175],"(SDR)":[176],"gains.":[177]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}