{"id":"https://openalex.org/W4225280365","doi":"https://doi.org/10.1109/icassp43922.2022.9746950","title":"An End-to-End Deep Learning Framework For Multiple Audio Source Separation And Localization","display_name":"An End-to-End Deep Learning Framework For Multiple Audio Source Separation And Localization","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225280365","doi":"https://doi.org/10.1109/icassp43922.2022.9746950"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746950","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/A5100401934","display_name":"Yu Chen","orcid":"https://orcid.org/0000-0001-5468-1380"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Chen","raw_affiliation_strings":["University of Michigan,USA","University of Michigan, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan,USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"University of Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427695","display_name":"Bowen Liu","orcid":"https://orcid.org/0000-0002-4194-8119"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bowen Liu","raw_affiliation_strings":["University of Michigan,USA","University of Michigan, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan,USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"University of Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100337456","display_name":"Zijian Zhang","orcid":"https://orcid.org/0000-0002-1634-9077"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zijian Zhang","raw_affiliation_strings":["University of Michigan,USA","University of Michigan, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan,USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"University of Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014196508","display_name":"Hun-Seok Kim","orcid":"https://orcid.org/0000-0002-6658-5502"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hun-Seok Kim","raw_affiliation_strings":["University of Michigan,USA","University of Michigan, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan,USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"University of Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4525,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.84230406,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"736","last_page":"740"},"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":0.9979000091552734,"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":0.9954000115394592,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multilateration","display_name":"Multilateration","score":0.9259092807769775},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.7809564471244812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7620917558670044},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7261068820953369},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.5912026762962341},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5273674130439758},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4849832057952881},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.45677322149276733},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.44936928153038025},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.43620216846466064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35298049449920654},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3363489508628845},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.28597527742385864},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1435236930847168},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.12369653582572937},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1010269820690155}],"concepts":[{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.9259092807769775},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.7809564471244812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7620917558670044},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7261068820953369},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.5912026762962341},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5273674130439758},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4849832057952881},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.45677322149276733},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.44936928153038025},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.43620216846466064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35298049449920654},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3363489508628845},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.28597527742385864},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1435236930847168},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.12369653582572937},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1010269820690155},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746950","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1844944916","https://openalex.org/W2104422351","https://openalex.org/W2129821199","https://openalex.org/W2130989868","https://openalex.org/W2170393302","https://openalex.org/W2460742184","https://openalex.org/W2772736377","https://openalex.org/W2810087991","https://openalex.org/W2810934215","https://openalex.org/W2884822476","https://openalex.org/W2888793942","https://openalex.org/W2963452667","https://openalex.org/W2964201867","https://openalex.org/W2981436548","https://openalex.org/W2990666817","https://openalex.org/W3011890046","https://openalex.org/W3027008958","https://openalex.org/W3042857426","https://openalex.org/W3094607766","https://openalex.org/W3096893582","https://openalex.org/W3105684258","https://openalex.org/W3163193264","https://openalex.org/W3163652268","https://openalex.org/W4320013936","https://openalex.org/W6629717138","https://openalex.org/W6679546383","https://openalex.org/W6732249622","https://openalex.org/W6751512325","https://openalex.org/W6777776875"],"related_works":["https://openalex.org/W2795050058","https://openalex.org/W2040378335","https://openalex.org/W4253838456","https://openalex.org/W3159506701","https://openalex.org/W3089904752","https://openalex.org/W4225280365","https://openalex.org/W3015225820","https://openalex.org/W2991037759","https://openalex.org/W1961041062","https://openalex.org/W3160140981"],"abstract_inverted_index":{"Sound":[0],"source":[1,81,114],"separation":[2,82,101,115],"and":[3,18,30,48,83],"localization":[4],"for":[5,64,77],"situational":[6],"awareness":[7],"enables":[8],"a":[9,88],"wide":[10],"range":[11],"of":[12,38,52,80],"applications":[13],"such":[14],"as":[15,116,118],"hearing":[16],"enhancement":[17],"audio":[19,33],"beam-forming.":[20],"We":[21],"present":[22],"an":[23],"end-to-end":[24],"deep":[25],"learning":[26],"framework":[27,42],"to":[28,70,97],"separate":[29],"localize":[31],"multiple":[32],"sources":[34,47],"from":[35],"the":[36,45,61,72,94,100,107],"mixture":[37],"multi-channels.":[39],"The":[40],"proposed":[41,108],"jointly":[43],"estimates":[44],"separated":[46],"their":[49],"time":[50],"difference":[51],"arrival":[53],"(TDOA)":[54],"at":[55],"different":[56],"microphones,":[57],"then":[58],"it":[59],"obtains":[60],"direction-of-arrival":[62],"(DOA)":[63],"each":[65],"source.":[66],"A":[67],"new":[68],"structure":[69],"reconstruct":[71],"mixed":[73],"signal":[74],"is":[75,91],"introduced":[76],"joint":[78],"optimization":[79],"TDOA":[84],"estimation.":[85,120],"In":[86],"addition,":[87],"discriminator":[89],"network":[90],"added":[92],"during":[93],"training":[95],"phase":[96],"further":[98],"improve":[99],"quality.":[102],"Experiment":[103],"results":[104],"demonstrate":[105],"that":[106],"method":[109],"achieves":[110],"state-of-the-art":[111],"accuracy":[112],"on":[113],"well":[117],"DOA":[119]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}