{"id":"https://openalex.org/W4224925594","doi":"https://doi.org/10.1109/icassp43922.2022.9746122","title":"Phase Shifted Bedrosian Filterbank: An Interpretable Audio Front-End for Time-Domain Audio Source Separation","display_name":"Phase Shifted Bedrosian Filterbank: An Interpretable Audio Front-End for Time-Domain Audio Source Separation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224925594","doi":"https://doi.org/10.1109/icassp43922.2022.9746122"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746122","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5038985810","display_name":"F\u00e9lix Mathieu","orcid":null},"institutions":[{"id":"https://openalex.org/I2801356230","display_name":"Thales (Australia)","ror":"https://ror.org/00f7vya03","country_code":"AU","type":"company","lineage":["https://openalex.org/I2801356230","https://openalex.org/I4210140930"]},{"id":"https://openalex.org/I4210140930","display_name":"Thales (France)","ror":"https://ror.org/04emwm605","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210140930"]}],"countries":["AU","FR"],"is_corresponding":false,"raw_author_name":"Felix Mathieu","raw_affiliation_strings":["Advanced Studies AI Lab,Thales SIX","Thales SIX GTS France (92230 Gennevilliers - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Studies AI Lab,Thales SIX","institution_ids":["https://openalex.org/I2801356230"]},{"raw_affiliation_string":"Thales SIX GTS France (92230 Gennevilliers - France)","institution_ids":["https://openalex.org/I4210140930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024072047","display_name":"Thomas Courtat","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140930","display_name":"Thales (France)","ror":"https://ror.org/04emwm605","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210140930"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thomas Courtat","raw_affiliation_strings":["T&#x00E9;l&#x00E9;com Paris, IP-Paris,LTCI","Thales SIX GTS France (92230 Gennevilliers - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"T&#x00E9;l&#x00E9;com Paris, IP-Paris,LTCI","institution_ids":["https://openalex.org/I4210165912"]},{"raw_affiliation_string":"Thales SIX GTS France (92230 Gennevilliers - France)","institution_ids":["https://openalex.org/I4210140930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055423112","display_name":"Ga\u00ebl Richard","orcid":"https://orcid.org/0000-0002-4960-0010"},"institutions":[{"id":"https://openalex.org/I2801356230","display_name":"Thales (Australia)","ror":"https://ror.org/00f7vya03","country_code":"AU","type":"company","lineage":["https://openalex.org/I2801356230","https://openalex.org/I4210140930"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]}],"countries":["AU","FR"],"is_corresponding":false,"raw_author_name":"Gael Richard","raw_affiliation_strings":["Advanced Studies AI Lab,Thales SIX","IP Paris - Institut Polytechnique de Paris (Route de Saclay, 91120 Palaiseau Cedex, France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Studies AI Lab,Thales SIX","institution_ids":["https://openalex.org/I2801356230"]},{"raw_affiliation_string":"IP Paris - Institut Polytechnique de Paris (Route de Saclay, 91120 Palaiseau Cedex, France - France)","institution_ids":["https://openalex.org/I4210145102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063097936","display_name":"Geoffroy Peeters","orcid":"https://orcid.org/0000-0001-5255-3019"},"institutions":[{"id":"https://openalex.org/I2801356230","display_name":"Thales (Australia)","ror":"https://ror.org/00f7vya03","country_code":"AU","type":"company","lineage":["https://openalex.org/I2801356230","https://openalex.org/I4210140930"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]}],"countries":["AU","FR"],"is_corresponding":false,"raw_author_name":"Geoffroy Peeters","raw_affiliation_strings":["Advanced Studies AI Lab,Thales SIX","IP Paris - Institut Polytechnique de Paris (Route de Saclay, 91120 Palaiseau Cedex, France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Studies AI Lab,Thales SIX","institution_ids":["https://openalex.org/I2801356230"]},{"raw_affiliation_string":"IP Paris - Institut Polytechnique de Paris (Route de Saclay, 91120 Palaiseau Cedex, France - France)","institution_ids":["https://openalex.org/I4210145102"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3631,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.46962543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"abs 2101 8596","issue":null,"first_page":"531","last_page":"535"},"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":0.9998999834060669,"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":0.9962999820709229,"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/filter-bank","display_name":"Filter bank","score":0.7031461000442505},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.6914187669754028},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6568670272827148},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.591065526008606},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5371826887130737},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5122160315513611},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4983980655670166},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.43294140696525574},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.42089059948921204},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4178627133369446},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4012526571750641},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23436182737350464},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.18837758898735046},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1200447678565979}],"concepts":[{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.7031461000442505},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6914187669754028},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6568670272827148},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.591065526008606},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5371826887130737},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5122160315513611},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4983980655670166},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.43294140696525574},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.42089059948921204},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4178627133369446},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4012526571750641},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23436182737350464},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.18837758898735046},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1200447678565979},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746122","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03708610v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03708610","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP, May 2022, Singapour, Singapore. &#x27E8;10.1109/ICASSP43922.2022.9746122&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1684575962","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2904818793","https://openalex.org/W2952218014","https://openalex.org/W2962901777","https://openalex.org/W2962935966","https://openalex.org/W2964052309","https://openalex.org/W2981976899","https://openalex.org/W2996969697","https://openalex.org/W3004940340","https://openalex.org/W3007948068","https://openalex.org/W3015199127","https://openalex.org/W3042857426","https://openalex.org/W3094607766","https://openalex.org/W3095717210","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3110614179","https://openalex.org/W4287372095","https://openalex.org/W6757424787","https://openalex.org/W6769511080","https://openalex.org/W6771792932","https://openalex.org/W6787166909","https://openalex.org/W6789403026"],"related_works":["https://openalex.org/W2963443859","https://openalex.org/W3132176577","https://openalex.org/W2114974607","https://openalex.org/W2614024025","https://openalex.org/W2150502936","https://openalex.org/W4300451326","https://openalex.org/W4381327731","https://openalex.org/W3112881379","https://openalex.org/W2158216966","https://openalex.org/W2002298560"],"abstract_inverted_index":{"The":[0],"use":[1,97],"of":[2,16,28,35,56,82,98],"a":[3,32,53],"parameterized":[4],"encoders":[5],"or":[6],"audio":[7],"front-ends":[8],"has":[9],"shown":[10],"promises":[11],"in":[12],"improving":[13],"the":[14,36,69,73,96,104],"interpretability":[15,63],"time":[17],"domain":[18],"single-channel":[19],"source":[20],"separation":[21],"models":[22],"such":[23,57],"as":[24],"Conv-TasNet.":[25],"This":[26],"type":[27],"filters":[29,42,83,100,110],"also":[30],"allows":[31,61,101],"potential":[33],"reduction":[34],"computational":[37],"cost":[38],"since":[39],"larger":[40],"encoder":[41,58],"can":[43],"be":[44],"used.":[45],"In":[46],"this":[47],"work,":[48],"we":[49,76],"propose":[50,77],"to":[51,78,102],"build":[52,79],"new":[54],"parameterization":[55],"filter-bank":[59],"which":[60],"gaining":[62],"while":[64],"keeping":[65],"flexibility.":[66],"Based":[67],"on":[68],"Hilbert":[70],"transform":[71],"and":[72,111],"Bedrosian":[74],"theorem,":[75],"phase-shifted":[80],"set":[81],"by":[84],"modulating":[85],"sinusoids":[86],"through":[87],"freely":[88],"learned":[89],"low":[90],"pass":[91],"filters.":[92,118],"We":[93],"show":[94],"that":[95],"these":[99],"keep":[103],"same":[105],"performances":[106],"when":[107,115],"using":[108,116],"small":[109],"even":[112],"improve":[113],"them":[114],"large":[117]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
