{"id":"https://openalex.org/W4312314091","doi":"https://doi.org/10.1109/mmsp55362.2022.9949050","title":"Blind Speech Separation Through Direction of Arrival Estimation Using Deep Neural Networks with a Flexibility on the Number of Speakers","display_name":"Blind Speech Separation Through Direction of Arrival Estimation Using Deep Neural Networks with a Flexibility on the Number of Speakers","publication_year":2022,"publication_date":"2022-09-26","ids":{"openalex":"https://openalex.org/W4312314091","doi":"https://doi.org/10.1109/mmsp55362.2022.9949050"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp55362.2022.9949050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp55362.2022.9949050","pdf_url":null,"source":{"id":"https://openalex.org/S4363605768","display_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","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":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","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/A5028088768","display_name":"Mohammed Hafsati","orcid":null},"institutions":[{"id":"https://openalex.org/I307854328","display_name":"Olea Medical (France)","ror":"https://ror.org/03w43f812","country_code":"FR","type":"company","lineage":["https://openalex.org/I307854328"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mohammed Hafsati","raw_affiliation_strings":["TUITO,La Ciotat,France","TUITO, La Ciotat, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TUITO,La Ciotat,France","institution_ids":["https://openalex.org/I307854328"]},{"raw_affiliation_string":"TUITO, La Ciotat, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044746566","display_name":"Kamil Bentounes","orcid":null},"institutions":[{"id":"https://openalex.org/I307854328","display_name":"Olea Medical (France)","ror":"https://ror.org/03w43f812","country_code":"FR","type":"company","lineage":["https://openalex.org/I307854328"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Kamil Bentounes","raw_affiliation_strings":["TUITO,La Ciotat,France","TUITO, La Ciotat, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TUITO,La Ciotat,France","institution_ids":["https://openalex.org/I307854328"]},{"raw_affiliation_string":"TUITO, La Ciotat, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013266148","display_name":"Ricard Marxer","orcid":"https://orcid.org/0000-0001-5099-5059"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I143002897","display_name":"Universit\u00e9 de Toulon","ror":"https://ror.org/02m9kbe37","country_code":"FR","type":"education","lineage":["https://openalex.org/I143002897"]},{"id":"https://openalex.org/I4210114274","display_name":"Laboratoire d\u2019Informatique et Syst\u00e8mes","ror":"https://ror.org/0257sgk90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I143002897","https://openalex.org/I21491767","https://openalex.org/I4210114274"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ricard Marxer","raw_affiliation_strings":["Universit&#x00E9; de Toulon, Aix Marseille Univ, CNRS, LIS,Toulon,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; de Toulon, Aix Marseille Univ, CNRS, LIS,Toulon,France","institution_ids":["https://openalex.org/I143002897","https://openalex.org/I4210114274","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9993000030517578,"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":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6268657445907593},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6150151491165161},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5647627115249634},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.48224931955337524},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.4726361632347107},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.45307445526123047},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.4327234625816345},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.428816556930542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.388355016708374},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36756378412246704},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25492048263549805},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1182478666305542}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6268657445907593},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6150151491165161},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5647627115249634},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.48224931955337524},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.4726361632347107},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.45307445526123047},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.4327234625816345},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.428816556930542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.388355016708374},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36756378412246704},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25492048263549805},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1182478666305542},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"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/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mmsp55362.2022.9949050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp55362.2022.9949050","pdf_url":null,"source":{"id":"https://openalex.org/S4363605768","display_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","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":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03948355v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03948355","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":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP), Sep 2022, Shanghai, China. pp.1-5, &#x27E8;10.1109/MMSP55362.2022.9949050&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G3570594198","display_name":"Microscopic Intelligibility Modeling","funder_award_id":"ANR-20-CE23-0012","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G4801681434","display_name":null,"funder_award_id":"ANR-20-CE23-0012-01","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W189850294","https://openalex.org/W285277413","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1887941968","https://openalex.org/W1897240248","https://openalex.org/W1901129140","https://openalex.org/W1981463705","https://openalex.org/W1987906574","https://openalex.org/W2075076415","https://openalex.org/W2104969945","https://openalex.org/W2156285962","https://openalex.org/W2158143227","https://openalex.org/W2159956319","https://openalex.org/W2164502538","https://openalex.org/W2289394825","https://openalex.org/W2337621096","https://openalex.org/W2398042854","https://openalex.org/W2626967530","https://openalex.org/W2786625961","https://openalex.org/W2810934215","https://openalex.org/W2884797218","https://openalex.org/W2909607850","https://openalex.org/W2963453742","https://openalex.org/W2963488660","https://openalex.org/W2987372735","https://openalex.org/W3025423009","https://openalex.org/W3036601975","https://openalex.org/W3115341864","https://openalex.org/W6631190155","https://openalex.org/W6639824700","https://openalex.org/W6703471520","https://openalex.org/W6728226663","https://openalex.org/W6739651123","https://openalex.org/W6777639356","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W4256429076","https://openalex.org/W1980381208","https://openalex.org/W1971174658","https://openalex.org/W2099195351","https://openalex.org/W2364594919","https://openalex.org/W2167092671","https://openalex.org/W2348092930","https://openalex.org/W1861706286","https://openalex.org/W2012063272","https://openalex.org/W3129272755"],"abstract_inverted_index":{"This":[0,109],"paper":[1],"presents":[2],"a":[3,56,85,124,128,133],"complete":[4],"framework":[5,119,147],"for":[6],"blind":[7],"multi-speaker":[8],"separation":[9,93],"in":[10,51,73,171,186],"reverberant":[11],"environments":[12],"using":[13,55,101,192],"neural":[14,58,88],"networks":[15],"while":[16],"being":[17],"flexible":[18],"on":[19,123,132],"the":[20,26,35,41,65,69,74,146,160],"number":[21],"of":[22,31,43,46,84,173,182,188],"sound":[23],"sources.":[24],"Under":[25],"W-disjoint":[27],"orthogonality":[28],"(WDO)":[29],"hypothesis":[30],"speech":[32,49],"signals,":[33],"with":[34,68,127,162],"proposed":[36],"framework,":[37],"we":[38,76],"first":[39],"estimate":[40,91],"direction":[42],"arrival":[44],"(DoA)":[45],"each":[47,52],"dominant":[48],"signal":[50,97,174],"time-frequency":[53],"bin":[54],"deep":[57,87],"network.":[59],"While":[60],"existing":[61],"state-of-the-art":[62,161],"methods":[63],"use":[64,79],"masks":[66],"associated":[67],"different":[70],"DoAs":[71],"directly":[72],"separation,":[75],"propose":[77],"to":[78,90,143,150,167,175,184],"them":[80],"as":[81],"input":[82],"features":[83],"second":[86],"network":[89],"refined":[92],"masks.":[94],"Each":[95],"speaker's":[96],"is":[98],"then":[99],"separated":[100],"an":[102,180],"estimated":[103],"Generalized":[104],"Eigenvalue":[105],"(GEV)":[106],"Wiener":[107],"filter.":[108],"approach":[110],"reduces":[111],"distortion,":[112],"interference,":[113],"and":[114,131,179],"artifacts.":[115],"We":[116],"assessed":[117],"our":[118,157],"through":[120],"numerical":[121],"experiments":[122,154],"simulated":[125],"dataset":[126,135],"comprehensive":[129],"analysis":[130],"real":[134],"acquired":[136],"from":[137],"recorded":[138],"spatial":[139],"room":[140],"impulse":[141],"responses":[142],"check":[144],"if":[145],"generalizes":[148],"well":[149],"actual":[151],"cases.":[152],"Numerical":[153],"show":[155],"that":[156],"contribution":[158],"outperforms":[159],"almost":[163],"<tex":[164,168],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[165,169],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$3dB$</tex>":[166],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$6dB$</tex>":[170],"terms":[172,187],"distortion":[176],"ratio":[177],"(SDR)":[178],"improvement":[181],"22%":[183],"26%":[185],"word":[189],"error":[190],"rate":[191],"wav2vec2":[193],"ASR":[194],"model.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}