{"id":"https://openalex.org/W3161003723","doi":"https://doi.org/10.1109/icassp39728.2021.9414105","title":"Auditory Filterbanks Benefit Universal Sound Source Separation","display_name":"Auditory Filterbanks Benefit Universal Sound Source Separation","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161003723","doi":"https://doi.org/10.1109/icassp39728.2021.9414105","mag":"3161003723"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5100452557","display_name":"Han Li","orcid":"https://orcid.org/0000-0001-5101-5542"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]},{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN","DE"],"is_corresponding":true,"raw_author_name":"Han Li","raw_affiliation_strings":["Audio Information Processing, Technical University of Munich, Munich, Germany","School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an, China","School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Audio Information Processing, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007763993","display_name":"Kean Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kean Chen","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an, China","School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031783799","display_name":"Bernhard U. Seeber","orcid":"https://orcid.org/0000-0002-3621-3409"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bernhard U. Seeber","raw_affiliation_strings":["Audio Information Processing, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Audio Information Processing, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100452557"],"corresponding_institution_ids":["https://openalex.org/I17145004","https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.9142,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73333333,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"88","issue":null,"first_page":"181","last_page":"185"},"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":0.9995999932289124,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.803188681602478},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.6986351609230042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6754477024078369},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6262480616569519},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5998422503471375},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.5676243901252747},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5672601461410522},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5026290416717529},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4312155246734619},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.34579145908355713},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3447122275829315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2751624584197998}],"concepts":[{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.803188681602478},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6986351609230042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6754477024078369},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6262480616569519},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5998422503471375},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.5676243901252747},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5672601461410522},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5026290416717529},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4312155246734619},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.34579145908355713},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3447122275829315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2751624584197998},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1612034","is_oa":false,"landing_page_url":"https://mediatum.ub.tum.de/1612034","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"ConferencePaper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5699999928474426,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W195624865","https://openalex.org/W1489184006","https://openalex.org/W1494198834","https://openalex.org/W1964538581","https://openalex.org/W2033708670","https://openalex.org/W2202261414","https://openalex.org/W2219249508","https://openalex.org/W2460742184","https://openalex.org/W2784225997","https://openalex.org/W2952218014","https://openalex.org/W2964052309","https://openalex.org/W2972541922","https://openalex.org/W2981976899","https://openalex.org/W2998657200","https://openalex.org/W3004940340","https://openalex.org/W3015199127","https://openalex.org/W3095717210","https://openalex.org/W3099330747","https://openalex.org/W4256399001","https://openalex.org/W4287632494","https://openalex.org/W6688816777"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W4390569940","https://openalex.org/W2888392564","https://openalex.org/W4361193272","https://openalex.org/W4310278675","https://openalex.org/W2036157531","https://openalex.org/W2103031592","https://openalex.org/W1967226023","https://openalex.org/W178436704","https://openalex.org/W3150394233"],"abstract_inverted_index":{"For":[0],"separating":[1],"two":[2],"arbitrary":[3],"sources":[4],"from":[5],"monaural":[6],"recordings,":[7],"the":[8,23,46,55,80,86,92,102,108,121,127],"encoder-separator-decoder":[9],"framework":[10],"is":[11],"popular":[12],"in":[13,22,145],"recent":[14],"years.":[15],"We":[16,29,83],"investigated":[17],"three":[18],"kinds":[19],"of":[20,48,69,112,143],"filterbanks":[21,50],"encoder:":[24],"free,":[25],"parameterized,":[26],"and":[27,33,42,114,130],"fixed.":[28],"proposed":[30],"parameterized":[31],"Gammatone":[32],"Gammachirp":[34],"filterbanks,":[35],"which":[36,138],"improved":[37],"performance":[38],"with":[39,63],"fewer":[40],"parameters":[41],"better":[43],"interpretability.":[44],"Next,":[45],"properties":[47,64,129],"different":[49],"were":[51],"investigated.":[52],"Through":[53],"training":[54],"network,":[56],"an":[57],"entirely":[58],"freely":[59],"learned":[60,90],"filterbank":[61,128],"emerges":[62],"similar":[65,78,135],"to":[66,79,136],"a":[67,74,95],"series":[68],"bandpass":[70],"filters":[71],"spaced":[72],"on":[73,107],"nonlinear":[75],"scale":[76],"-":[77],"auditory":[81,97],"system.":[82],"also":[84],"explored":[85],"underlying":[87],"separation":[88,122,131],"mechanisms":[89,132],"by":[91],"network":[93,123],"through":[94],"classic":[96],"segregation":[98],"experiment,":[99],"revealing":[100],"that":[101,120,133],"model":[103],"separates":[104],"mixtures":[105],"based":[106],"general":[109],"principle":[110],"(proximity":[111],"frequency":[113],"time).":[115],"In":[116],"summary,":[117],"results":[118],"demonstrate":[119],"automatically":[124],"picks":[125],"up":[126],"are":[134],"those":[137],"have":[139],"developed":[140],"over":[141],"millions":[142],"years":[144],"humans.":[146]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
