{"id":"https://openalex.org/W4310337937","doi":"https://doi.org/10.1109/avss56176.2022.9959632","title":"Improved Separation of Closely-spaced Speakers by Exploiting Auxiliary Direction of Arrival Information within a U-Net Architecture","display_name":"Improved Separation of Closely-spaced Speakers by Exploiting Auxiliary Direction of Arrival Information within a U-Net Architecture","publication_year":2022,"publication_date":"2022-11-24","ids":{"openalex":"https://openalex.org/W4310337937","doi":"https://doi.org/10.1109/avss56176.2022.9959632"},"language":"en","primary_location":{"id":"doi:10.1109/avss56176.2022.9959632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/avss56176.2022.9959632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 18th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/01GQ22BEA3QZD0J7QZ002P6ANC/file/01GQ22E6Q0ERBH99RX5W2W1VK0.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012036252","display_name":"Stijn Kindt","orcid":"https://orcid.org/0000-0001-9300-4251"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Stijn Kindt","raw_affiliation_strings":["Ghent University - imec,IDLab, Department of Electronics and Information Systems,Ghent,Belgium","IDLab, Department of Electronics and Information Systems, Ghent University - imec, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab, Department of Electronics and Information Systems,Ghent,Belgium","institution_ids":["https://openalex.org/I32597200","https://openalex.org/I39327780"]},{"raw_affiliation_string":"IDLab, Department of Electronics and Information Systems, Ghent University - imec, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071309390","display_name":"Alexander Bohlender","orcid":"https://orcid.org/0000-0003-1819-0482"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Alexander Bohlender","raw_affiliation_strings":["Ghent University - imec,IDLab, Department of Electronics and Information Systems,Ghent,Belgium","IDLab, Department of Electronics and Information Systems, Ghent University - imec, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab, Department of Electronics and Information Systems,Ghent,Belgium","institution_ids":["https://openalex.org/I32597200","https://openalex.org/I39327780"]},{"raw_affiliation_string":"IDLab, Department of Electronics and Information Systems, Ghent University - imec, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081844255","display_name":"Nilesh Madhu","orcid":"https://orcid.org/0000-0001-9131-3309"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Nilesh Madhu","raw_affiliation_strings":["Ghent University - imec,IDLab, Department of Electronics and Information Systems,Ghent,Belgium","IDLab, Department of Electronics and Information Systems, Ghent University - imec, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab, Department of Electronics and Information Systems,Ghent,Belgium","institution_ids":["https://openalex.org/I32597200","https://openalex.org/I39327780"]},{"raw_affiliation_string":"IDLab, Department of Electronics and Information Systems, Ghent University - imec, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9223,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75639967,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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/microphone-array","display_name":"Microphone array","score":0.7656068801879883},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7435848116874695},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.6629042625427246},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6207282543182373},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5679318904876709},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5091137290000916},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.498795747756958},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4783351421356201},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35218244791030884},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1791553795337677},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.06144183874130249}],"concepts":[{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.7656068801879883},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7435848116874695},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.6629042625427246},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6207282543182373},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5679318904876709},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5091137290000916},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.498795747756958},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4783351421356201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35218244791030884},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1791553795337677},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.06144183874130249},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C21822782","wikidata":"https://www.wikidata.org/wiki/Q131214","display_name":"Antenna (radio)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/avss56176.2022.9959632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/avss56176.2022.9959632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 18th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:01GQ22BEA3QZD0J7QZ002P6ANC","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/01GQ22BEA3QZD0J7QZ002P6ANC","pdf_url":"https://biblio.ugent.be/publication/01GQ22BEA3QZD0J7QZ002P6ANC/file/01GQ22E6Q0ERBH99RX5W2W1VK0.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9781665463829","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:01GQ22BEA3QZD0J7QZ002P6ANC","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/01GQ22BEA3QZD0J7QZ002P6ANC","pdf_url":"https://biblio.ugent.be/publication/01GQ22BEA3QZD0J7QZ002P6ANC/file/01GQ22E6Q0ERBH99RX5W2W1VK0.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9781665463829","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8050015315","display_name":"Robust speech capture and enhancement using ad hoc distributed microphone arrays by integrating and embedding domain-specific signal models within deep-learning frameworks","funder_award_id":"G081420N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4310337937.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W123936940","https://openalex.org/W1552314771","https://openalex.org/W1982172017","https://openalex.org/W2030486566","https://openalex.org/W2067295501","https://openalex.org/W2071608040","https://openalex.org/W2125768106","https://openalex.org/W2127851351","https://openalex.org/W2291372403","https://openalex.org/W2403891086","https://openalex.org/W2460742184","https://openalex.org/W2763188033","https://openalex.org/W2889442120","https://openalex.org/W2945191446","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2964199361","https://openalex.org/W2972947281","https://openalex.org/W2987372735","https://openalex.org/W3097653961","https://openalex.org/W3099330747","https://openalex.org/W3127686677","https://openalex.org/W3138975519","https://openalex.org/W3139695047","https://openalex.org/W3153427259","https://openalex.org/W3160085755","https://openalex.org/W3160129476","https://openalex.org/W3213559049","https://openalex.org/W6667418930","https://openalex.org/W6789826613","https://openalex.org/W6793651609"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2011788874","https://openalex.org/W2041060376","https://openalex.org/W2963983801","https://openalex.org/W3119734852"],"abstract_inverted_index":{"Microphone":[0],"arrays":[1],"use":[2],"spatial":[3],"diversity":[4],"for":[5,54,133],"separating":[6,134],"concurrent":[7],"audio":[8],"sources.":[9,137],"Source":[10],"signals":[11],"from":[12],"different":[13],"directions":[14],"of":[15,64,122,130],"arrival":[16],"(DOAs)":[17],"are":[18],"captured":[19],"with":[20,118],"DOA-dependent":[21],"time-delays":[22],"between":[23,101],"the":[24,31,86,90,97,102,105,123,128],"microphones.":[25,103],"These":[26],"can":[27,93,107],"be":[28,94],"exploited":[29],"in":[30],"short-time":[32],"Fourier":[33],"transform":[34],"domain":[35],"to":[36,71,88],"yield":[37],"time-frequency":[38],"masks":[39],"that":[40],"extract":[41],"a":[42,109,119],"target":[43],"signal":[44],"while":[45],"suppressing":[46],"unwanted":[47],"components.":[48],"Using":[49],"deep":[50],"neural":[51],"networks":[52],"(DNNs)":[53],"mask":[55],"estimation":[56],"has":[57],"drastically":[58],"improved":[59],"separation":[60,63],"performance.":[61],"However,":[62],"closely":[65,135],"spaced":[66,136],"sources":[67],"remains":[68],"difficult":[69],"due":[70],"their":[72],"similar":[73],"inter-microphone":[74],"time":[75],"delays.":[76],"We":[77],"propose":[78],"using":[79],"auxiliary":[80],"information":[81,132],"on":[82,113],"source":[83],"DOAs":[84],"within":[85],"DNN":[87,106],"improve":[89],"separation.":[91],"This":[92],"encoded":[95],"by":[96],"expected":[98],"phase":[99],"differences":[100],"Alternatively,":[104],"learn":[108],"suitable":[110],"input":[111],"representation":[112],"its":[114],"own":[115],"when":[116],"provided":[117],"multi-hot":[120],"encoding":[121],"DOAs.":[124],"Experimental":[125],"results":[126],"demonstrate":[127],"benefit":[129],"this":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}